add EMBEDDING_BASE_URL

Merge branch 'feature/multimodal-image-input' into developing
feat: support multimodal image (base64) input in chat API
2026-06-18 14:56:27 +08:00 · 2026-06-18 12:54:31 +08:00 · 2026-06-18 11:34:57 +08:00 · 2026-06-16 15:47:52 +08:00 · 2026-06-16 13:22:12 +08:00 · 2026-06-16 13:19:23 +08:00
16 changed files with 344 additions and 872 deletions
--- a/.features/skill/MEMORY.md
+++ b/.features/skill/MEMORY.md
@ -1,6 +1,8 @@
 # Skill 功能

 > 负责范围：技能包管理服务 - 核心实现
+> 最后更新：2026-06-07
+> 最后更新：2026-06-02
 > 最后更新：2026-05-26

 ## 当前状态
@ -24,9 +26,15 @@ MCP UI 类 skill 已按 MCP Apps 模式改造：工具返回数据，静态 HTML
 - `skills_developing/` - 开发中 skills
 - `agent/subagent_loader.py` - 扫描 skill `agents/*.md` 加载子 agent（2026-05 引入）
 - `agent/mcp_trace_meta.py` - 对 `ClientSession.call_tool` 做 monkey-patch，向 `rag_retrieve` / `table_rag_retrieve` 的 MCP `_meta` 注入 `trace_id`（2026-05 引入）
+- `agent/tool_metrics_middleware.py` - `ToolMetricsMiddleware` 给每次 tool 调用 emit `catalog_agent.tool_call` 结构化指标（2026-05 引入）

 ## 最近重要事项

+- [2026-06-07](changelog/2026-Q2.md): 新增 `table-query` skill——`skills/developing/table-query/`，SQLite 表查询三步式工作流（search-tables → get-schemas → run-sql），run-sql 接收 JSON plan via stdin heredoc 避免 shell 转义；`category: Data & Retrieval`（`bb74aee`）
+- [2026-06-05](changelog/2026-Q2.md): 新增 `mineru` skill——`skills/developing/mineru/`，PDF/Office/图片转 Markdown，自动路由免 token 的 Agent API 与需 token 的 Standard API，附 15 个目标 sink（notion/feishu/slack/...）；`category: Document Processing`（`b618cb1`）
+- [2026-06-05](changelog/2026-Q2.md): `rag-retrieve` 系列空 query 由 JSON-RPC error 改为 success-with-error-text——5 个 server 变体（autoload/onprem、autoload/support、developing/rag-retrieve-no-citation、onprem/rag-retrieve-only、support/rag-retrieve-only）统一改用 `create_success_response` 携带 `"Error: missing required parameter 'query'..."` 文案，让 agent 在 tool output 里看到错误并自纠错重试（`ecf332a`）
+- [2026-06-02](changelog/2026-Q2.md): 修复 deepagents 落盘 backend grep 扫描全盘问题——`create_custom_cli_agent` 中 `large_results_backend` / `conversation_history_backend` 的 `FilesystemBackend` 由 `virtual_mode=False` 改为 `True`，避免 `CompositeBackend` 剥前缀后把 `"/"` 转发给 grep 时扫到真实根目录，单次 grep 从 45–152s 回到毫秒级（`6bccd89`）
+- [2026-05-29](changelog/2026-Q2.md): 新增 `ToolMetricsMiddleware`——通过 `wrap_tool_call` / `awrap_tool_call` 对每次 tool 调用计时并 emit `catalog_agent.tool_call` 结构化指标（成功/失败/取消三态、含 `tool_name`/`trace_id`/`bot_id`/`duration_ms`/`error_type`）；插在 `init_agent` 中间件链的 `EmptyResponseRetryMiddleware` 之后、`ToolUseCleanupMiddleware` 之前（`9f0ae25`）
 - [2026-05-26](changelog/2026-Q2.md): skill 引入 `category` 字段——`routes/skill_manager.py` 在 `SkillItem` / `SkillValidationResult` 增加 `category`，从 `plugin.json` 与 `SKILL.md` frontmatter 解析，official skill 默认 `"other"`、user skill 默认 `"custom"`；并通过 batch 给 common/developing/onprem/support 路径下大量 skill 元数据补 `category`，`data-dashboard` / `mcp-ui` 归类 `Interactive UI`（`203dcf4`, `3ada55a`, `9658588`）
 - [2026-05-26](changelog/2026-Q2.md): developing 分支大合并新增多个 skill：`ai-ppt-generator`（百度 AI PPT）、`nfc-medicine-lookup`（NFC 药品检索）、`ppt-outline`（PPT 大纲 / HTML 演示文稿）、`z-card-image`（配图 / 卡片图），同时 `skills/linggan/*` 系列 skill 经合并回归（`3ada55a`）
 - [2026-05-23](changelog/2026-Q2.md): 新增 MCP App 型 `skills/developing/ecommerce-storefront/`——含 `product-list` / `order-confirm` 两个 HTML App + 自带 `ecommerce_server.py` MCP server；同时落地 `docs/mcp-app-training.md`（约 1063 行）作为 MCP App 培训材料（`9d001c8`）
@ -86,6 +94,9 @@ MCP UI 类 skill 已按 MCP Apps 模式改造：工具返回数据，静态 HTML
 - ⚠️ **skill `category` 默认值**：API 返回的 `SkillItem.category`——official skill fallback 为 `"other"`、user skill fallback 为 `"custom"`；前端做分类视图时需要同时识别这两个 sentinel，不要假设官方/用户 skill 用同一套缺省值。
 - ⚠️ **`category` 字段双入口**：同一 skill 可以同时在 `.claude-plugin/plugin.json` 和 `SKILL.md` frontmatter 写 `category`；`get_skill_metadata` 优先走 `parse_plugin_json`，若 skill 包没有 plugin.json 才回落到 `parse_skill_frontmatter`——两者写不一致时以 plugin.json 为准。
 - ⚠️ **Daytona shell_env 是文件注入而非 process env**：`init_agent` 通过 `cat > $REMOTE_BASH_ENV_PATH` 写入 `export VAR=...` 行，沙箱内必须由 shell（bash）的 `BASH_ENV` 加载才能生效；非 daytona 模式或不走 bash 启动的脚本拿不到这些变量。扩展注入项需直接改 `init_agent` 里的 `_shell_env` 字典。
+- ⚠️ **`CompositeBackend` 路由下的落盘 backend 必须 `virtual_mode=True`**：`create_custom_cli_agent` 中 `large_results_backend` / `conversation_history_backend` 都用独立 `tempfile.mkdtemp()` 做根目录，但 `CompositeBackend` 在路由时会剥掉前缀、可能把 `"/"` 转发给 grep；`virtual_mode=False` 会把 `"/"` 解析为真实根目录并扫到 `/usr`、`/var`、其他会话的 tmp 目录（单次 45–152s）。`virtual_mode=True` 才会把所有路径锚定到 `root_dir` 并过滤越界结果。后续新增"只服务本次会话"的落盘 backend 一律走 `virtual_mode=True`，真实 workspace backend 仍保持 `False`。
+- ⚠️ **`ToolMetricsMiddleware` 必须在重试中间件之后、其他工具中间件之前**：`init_agent` 中顺序约定为 `EmptyResponseRetryMiddleware → ToolMetricsMiddleware → ToolUseCleanupMiddleware → ...`，这样统计到的 `duration_ms` 才包含全部后续 tool 处理开销并自然覆盖重试边界。指标 emit 自身的异常被吞掉只打 logger.exception，所以指标缺失不会触发 agent 报错，必须在指标后端做独立告警。
+- ⚠️ **`rag-retrieve` 系列空 query 返回 success 而非 JSON-RPC error**：5 个 server 变体（autoload/onprem、autoload/support、developing/rag-retrieve-no-citation、onprem/rag-retrieve-only、support/rag-retrieve-only）从 2026-06-05 起，缺 `query` 参数时返回 `create_success_response` 携带 `content[].text` 前缀 `"Error: missing required parameter 'query'..."`，故意让 LLM agent 在 tool output 里看到错误并自纠错重试。下游/中间层不能再用 JSON-RPC `error.code == -32602` 判断缺参，需要从 text 内容解析；新 MCP server 设计错误路径时也应区分"需要 agent 自纠错的语义错误（走 success-with-error-text）"与"不可恢复错误（走 error response）"。

 ## Skill 目录结构

--- a/.features/skill/changelog/2026-Q2.md
+++ b/.features/skill/changelog/2026-Q2.md
@ -4,6 +4,143 @@

 ---

+## 2026-06-07: 新增 `table-query` skill（SQLite 表查询）
+
+**类型**：新功能
+
+**背景**：bot 上传的 Excel/CSV 表格此前只能走 `rag_retrieve` 语义检索回答问题，对"价格/数量/库存/排名/聚合"这类**结构化**问题精度差、答非所问。需要一条"快速、不走 LLM 的 SQL 查询路径"。
+
+**改动**：
+- 新增 `skills/developing/table-query/`：
+  - `SKILL.md`：定义 search-tables → get-schemas → run-sql 三步工作流；明确"backend 不做 LLM 推理，由 agent 自己写 SQLite SQL"；`category: Data & Retrieval`。
+  - `scripts/table_query.py`：CLI 入口 + run-sql plan 执行器（plan 通过 stdin heredoc 传递，无需 shell 转义）。
+  - `skill.yaml`：元数据。
+  - `verify_table_query.sh`：自检脚本。
+- 工作流要求：search-tables **每问最多 1 次**，run-sql 出错重试 ≤ 2 次，且不回退到 search-tables；search-tables 无果时降级到 `rag_retrieve`。
+
+**根因**：N/A（新功能）
+
+**影响**：
+- agent 可直接对上传表数据做 SUM/AVG/COUNT 等结构化查询，并通过 `__src` 列 + `file_ref_table` 输出行级 citation。
+- 同时引入 plan-on-stdin 的调用约定（`<<'PLAN' ... PLAN`），后续类似 SQL/JSON 入参的 skill 可参考此模式以避免 argv 转义问题。
+
+**相关文件**：
+- `skills/developing/table-query/SKILL.md`
+- `skills/developing/table-query/scripts/table_query.py`
+- `skills/developing/table-query/skill.yaml`
+- `skills/developing/table-query/verify_table_query.sh`
+
+**Commit/PR**：`bb74aee`
+
+---
+
+## 2026-06-05: 新增 `mineru` skill（PDF/Office/图片 → Markdown 解析）
+
+**类型**：新功能
+
+**背景**：缺少统一的"文档转 Markdown"管道，PDF/Word/PPT/Excel/图片需要走不同工具，且 OCR / 公式 / 表格识别能力不一致。
+
+**改动**：
+- 新增 `skills/developing/mineru/`（约 4700 行，30 文件）：
+  - `SKILL.md` + `references/`（api_reference / comparison / integrations）。
+  - `scripts/mineru.py`：核心 CLI，自动路由 Agent API（无 token）与 Standard API（需 `MINERU_TOKEN`，支持大文件/批量/DOCX/HTML/LaTeX 导出）。
+  - `scripts/mineru_mcp.py`：MCP server 包装。
+  - `scripts/sinks/`：airtable / coda / confluence / dingtalk / feishu / linear / local / notion / onenote / roam / siyuan / slack / ticktick / wecom / wps / yuque 等多目标写出。
+  - `scripts/chunking.py` / `splitter.py` / `local_engine.py`：分块、切分、本地引擎。
+- `category: Document Processing`，标准依赖（仅标准库）。
+
+**根因**：N/A（新功能）
+
+**影响**：
+- 提供"零 token 起步、有 token 升级"的渐进式解析路径，降低部署门槛。
+- 多 sink 设计可作为后续"采集 → 结构化 → 多目的地分发"类 skill 的参考骨架。
+
+**相关文件**：
+- `skills/developing/mineru/SKILL.md`
+- `skills/developing/mineru/scripts/mineru.py`
+- `skills/developing/mineru/scripts/mineru_mcp.py`
+- `skills/developing/mineru/scripts/sinks/*.py`（15 个目标）
+
+**Commit/PR**：`b618cb1`
+
+---
+
+## 2026-06-05: `rag-retrieve` 系列空 query 改返回 success 文案（替代 JSON-RPC error）
+
+**类型**：行为变更（兼容性）
+
+**背景**：`rag_retrieve` / `table_rag_retrieve` 工具在缺少 `query` 参数时返回 JSON-RPC `-32602` error。MCP/agent 链路上 error 容易被上层吞掉，agent 看不到"为什么失败"，无法自我修复。
+
+**改动**：把 5 个 rag-retrieve server 变体的"missing query"分支由 `create_error_response(-32602, ...)` 改为 `create_success_response(...)` 携带 `content[].text = "Error: missing required parameter 'query'. Please call this tool again with a non-empty 'query' argument describing what you want to retrieve."`：
+- `skills/autoload/onprem/rag-retrieve/rag_retrieve_server.py`
+- `skills/autoload/support/rag-retrieve/rag_retrieve_server.py`
+- `skills/developing/rag-retrieve-no-citation/rag_retrieve_server.py`
+- `skills/onprem/rag-retrieve-only/rag_retrieve_server.py`
+- `skills/support/rag-retrieve-only/rag_retrieve_server.py`
+
+**根因**：MCP 协议层的 error 在多数 agent 框架下不会作为"tool 返回结果"传给 LLM，从而无法触发重试；改成 success-with-error-text 让 agent 把错误文本当 tool output 读到，并在下一轮自然带上 query 重试。
+
+**影响**：
+- 客户端**不能再依赖 JSON-RPC error code = -32602 判定缺参**，必须从 `content[].text` 前缀 `"Error:"` 解析；任何在 success 路径上做强校验/落盘的中间层需要兼容这种"假成功"形态。
+- 新 MCP server 出错路径如果是"需要 agent 自纠错"的语义错误，应走同样的 success-with-error-text 模式；底层崩溃 / 不可恢复错误仍走 error response。
+
+**相关文件**：见上。
+
+**Commit/PR**：`ecf332a`
+
+---
+
+## 2026-06-02: 修复 deepagents 落盘 backend grep 扫描全盘问题（virtual_mode=True）
+
+**类型**：Bug 修复
+
+**背景**：`create_custom_cli_agent` 给 `large_results` / `conversation_history` 两个路由创建了独立 `FilesystemBackend(tempfile.mkdtemp(...), virtual_mode=False)`，配合 `CompositeBackend` 做前缀路由。线上出现 grep 调用耗时 45–152s 的异常。
+
+**改动**：将 `large_results_backend` 与 `conversation_history_backend` 的 `virtual_mode` 由 `False` 改为 `True`，并在调用处补 NOTE 注释说明 virtual_mode 的语义。
+
+**根因**：`CompositeBackend` 会先剥掉路由前缀，再把剩余路径（极端情况下就是 `"/"`）转发给被路由 backend 的 grep。当 backend 的 `virtual_mode=False` 时，`"/"` 解析为真实根目录而不是 `root_dir`，于是 grep 在沙箱 / 容器内对 `/usr`、`/var`、其他会话的 tmp 目录全盘扫描，单次耗时达数十秒到分钟级。`virtual_mode=True` 会把所有路径锚定到 `root_dir`，并过滤掉根目录之外的结果，把扫描限制在 backend 自己的 tmp 子目录内。
+
+**影响**：
+- 这两个 backend 的 grep 调用回落到毫秒级，整个 deep agent 的 tool 调用 P99 大幅下降。
+- 任何新增的"落盘但只服务于本次会话"的 `FilesystemBackend` 走 `CompositeBackend` 路由时，**必须**使用 `virtual_mode=True`，否则容易复现同样的全盘扫描问题。
+- 真实 workspace backend（用户文件根目录）仍然是 `virtual_mode=False`，因为它需要看到沙箱真实路径上的产物。
+
+**相关文件**：
+- `agent/deep_assistant.py`
+
+**Commit/PR**：`6bccd89`
+
+---
+
+## 2026-05-29: 新增 ToolMetricsMiddleware（tool 调用埋点）
+
+**类型**：新功能
+
+**背景**：deep agent 内部的工具调用（含 MCP tool / skill script / 文件系统操作等）此前缺少统一的耗时与成功率埋点；问题排查只能依赖日志，无法对接 `emit_question_metric` 的结构化指标体系。
+
+**改动**：
+- 新增 `agent/tool_metrics_middleware.py`，定义 `ToolMetricsMiddleware(AgentMiddleware)`：
+  - 同时实现 `wrap_tool_call`（同步）与 `awrap_tool_call`（异步）。
+  - 对每次 tool 调用计时（`time.monotonic()`），通过 `emit_question_metric(stage="catalog_agent.tool_call", ...)` 上报：`status`（`success` / `error` / `cancel`）、`duration_ms`、`error_type`、`tool_name`、`tool_call_id`、`trace_id`、`bot_id`、`session_id`、`model`、`stream`、`tool_response`、`enable_thinking`。
+  - 异步分支特别捕获 `asyncio.CancelledError` 上报 `status="cancel"` 后再 re-raise。
+  - 指标 emit 自身的异常被 try/except 兜住，绝不影响 tool 调用本体。
+- `agent/deep_assistant.py::init_agent` 中间件链中，将 `ToolMetricsMiddleware(config)` 插在 `EmptyResponseRetryMiddleware` 之后、`ToolUseCleanupMiddleware` 之前。
+
+**根因**：N/A（新功能）
+
+**影响**：
+- 所有走 deep agent / sub agent 的 tool 调用现在都会自动出 `catalog_agent.tool_call` 结构化指标，可在指标后端按 `tool_name` / `bot_id` / `status` 聚合做 P50 / P99 / 错误率分析。
+- 中间件顺序硬约束扩展：`EmptyResponseRetryMiddleware → ToolMetricsMiddleware → ToolUseCleanupMiddleware → CustomFilesystemMiddleware → SubAgentMiddleware → AnthropicPromptCachingMiddleware`，调整 `init_agent` 中间件顺序时需保持 `ToolMetricsMiddleware` 在最外层（仅次于重试），否则统计到的耗时不包含其他中间件开销。
+- emit 失败只打 logger.exception，不会回传给 tool handler；指标缺失需在指标后端层面单独告警，不要依赖 agent 端口的报错。
+
+**相关文件**：
+- `agent/tool_metrics_middleware.py`（新增）
+- `agent/deep_assistant.py`
+
+**Commit/PR**：`9f0ae25`
+
+---
+
 ## 2026-05-26: skill `category` 字段全面接入

 **类型**：新功能
--- a/agent/checkpoint_utils.py
+++ b/agent/checkpoint_utils.py
@ -90,6 +90,8 @@ async def prepare_checkpoint_message(config, checkpointer):
        last_user_msg = next((m for m in reversed(config.messages) if m.get('role') == 'user'), None)
        if last_user_msg:
            config.messages = [last_user_msg]
-            logger.info(f"Has history, sending last user message: {last_user_msg.get('content', '')[:50]}...")
+            from utils.fastapi_utils import extract_text_from_content
+            preview = extract_text_from_content(last_user_msg.get('content', ''))
+            logger.info(f"Has history, sending last user message: {preview[:50]}...")
    else:
        logger.info(f"No history, sending all {len(config.messages)} messages")
--- a/agent/deep_assistant.py
+++ b/agent/deep_assistant.py
@ -18,7 +18,6 @@ from langgraph.store.base import BaseStore
 from langchain.agents.middleware import SummarizationMiddleware as LangchainSummarizationMiddleware
 from .summarization_middleware import SummarizationMiddleware
 from langchain_mcp_adapters.client import MultiServerMCPClient
-from sympy.printing.cxx import none
 from utils.fastapi_utils import detect_provider, sanitize_model_kwargs
 from .guideline_middleware import GuidelineMiddleware
 from .tool_output_length_middleware import ToolOutputLengthMiddleware
--- a/agent/mem0_manager.py
+++ b/agent/mem0_manager.py
@ -120,6 +120,37 @@ except Exception as e:
    logger.warning(f"Failed to patch mem0 remove_code_blocks: {e}")


+# Monkey patch: make PGVector.__del__ tolerate cur/conn being None.
+# This project shares a single psycopg2 pool and explicitly sets vector_store.cur
+# and vector_store.conn to None after releasing the connection. mem0's original
+# __del__ calls self.cur.close() without a None check, raising a harmless but noisy
+# "Exception ignored in __del__: AttributeError" when the instance is garbage
+# collected. This replacement releases resources only when they still exist.
+def _safe_pgvector_del(self) -> None:
+    """Safely close PGVector cursor/connection, tolerating None values."""
+    try:
+        cur = getattr(self, "cur", None)
+        if cur is not None:
+            cur.close()
+        conn = getattr(self, "conn", None)
+        if conn is not None:
+            conn.close()
+    except Exception:
+        # Never raise from __del__; ignore any teardown errors
+        pass
+
+
+try:
+    import mem0.vector_stores.pgvector as mem0_pgvector
+    mem0_pgvector.PGVector.__del__ = _safe_pgvector_del
+    logger.info("Successfully patched mem0 PGVector.__del__ to tolerate None cur/conn")
+except ImportError:
+    # mem0 pgvector module not available; nothing to patch
+    pass
+except Exception as e:
+    logger.warning(f"Failed to patch mem0 PGVector.__del__: {e}")
+
+
 class Mem0Manager:
    """
    Mem0 connection and instance manager
--- a/docker-compose-with-pgsql.yml
+++ b/docker-compose-with-pgsql.yml
@ -41,6 +41,10 @@ services:
      - CHECKPOINT_DB_URL=postgresql://postgres:E5ACJo6zJub4QS@postgres:5432/agent_db
      - NEW_API_BASE_URL=http://host.docker.internal:3001
      - R2_UPLOAD_CONFIG=/app/config/local-upload.yaml
+      - EMBEDDING_BASE_URL=https://api.siliconflow.cn/v1
+      - EMBEDDING_API_KEY=sk-bybtvfdvqaonwknqnuhfsdmceliebvggjkaizkxkxkxolysf
+      - EMBEDDING_MODEL_NAME=BAAI/bge-large-zh-v1.5
+      - EMBEDDING_DIMENSIONS=1024
    volumes:
      # Mount project data directories
      - ./projects:/app/projects
--- a/poetry.lock
+++ b/poetry.lock
@ -1163,18 +1163,6 @@ all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>
 standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
 standard-no-fastapi-cloud-cli = ["email-validator (>=2.0.0)", "fastapi-cli[standard-no-fastapi-cloud-cli] (>=0.0.8)", "httpx (>=0.23.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]

-[[package]]
-name = "filelock"
-version = "3.29.0"
-description = "A platform independent file lock."
-optional = false
-python-versions = ">=3.10"
-groups = ["main"]
-files = [
-    {file = "filelock-3.29.0-py3-none-any.whl", hash = "sha256:96f5f6344709aa1572bbf631c640e4ebeeb519e08da902c39a001882f30ac258"},
-    {file = "filelock-3.29.0.tar.gz", hash = "sha256:69974355e960702e789734cb4871f884ea6fe50bd8404051a3530bc07809cf90"},
-]
-
 [[package]]
 name = "filetype"
 version = "1.2.0"
@ -1339,46 +1327,6 @@ files = [
    {file = "frozenlist-1.8.0.tar.gz", hash = "sha256:3ede829ed8d842f6cd48fc7081d7a41001a56f1f38603f9d49bf3020d59a31ad"},
 ]

-[[package]]
-name = "fsspec"
-version = "2026.4.0"
-description = "File-system specification"
-optional = false
-python-versions = ">=3.10"
-groups = ["main"]
-files = [
-    {file = "fsspec-2026.4.0-py3-none-any.whl", hash = "sha256:11ef7bb35dab8a394fde6e608221d5cf3e8499401c249bebaeaad760a1a8dec2"},
-    {file = "fsspec-2026.4.0.tar.gz", hash = "sha256:301d8ac70ae90ef3ad05dcf94d6c3754a097f9b5fe4667d2787aa359ec7df7e4"},
-]
-
-[package.extras]
-abfs = ["adlfs"]
-adl = ["adlfs"]
-arrow = ["pyarrow (>=1)"]
-dask = ["dask", "distributed"]
-dev = ["pre-commit", "ruff (>=0.5)"]
-doc = ["numpydoc", "sphinx", "sphinx-design", "sphinx-rtd-theme", "yarl"]
-dropbox = ["dropbox", "dropboxdrivefs", "requests"]
-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs (>2024.2.0)", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs (>2024.2.0)", "smbprotocol", "tqdm"]
-fuse = ["fusepy"]
-gcs = ["gcsfs (>2024.2.0)"]
-git = ["pygit2"]
-github = ["requests"]
-gs = ["gcsfs"]
-gui = ["panel"]
-hdfs = ["pyarrow (>=1)"]
-http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"]
-libarchive = ["libarchive-c"]
-oci = ["ocifs"]
-s3 = ["s3fs (>2024.2.0)"]
-sftp = ["paramiko"]
-smb = ["smbprotocol"]
-ssh = ["paramiko"]
-test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"]
-test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"]
-test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "backports-zstd ; python_version < \"3.14\"", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas (<3.0.0)", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard ; python_version < \"3.14\""]
-tqdm = ["tqdm"]
-
 [[package]]
 name = "google-auth"
 version = "2.52.0"
@ -1726,45 +1674,6 @@ files = [
 hpack = ">=4.1,<5"
 hyperframe = ">=6.1,<7"

-[[package]]
-name = "hf-xet"
-version = "1.5.0"
-description = "Fast transfer of large files with the Hugging Face Hub."
-optional = false
-python-versions = ">=3.8"
-groups = ["main"]
-markers = "platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\""
-files = [
-    {file = "hf_xet-1.5.0-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:7d70fe2ce97b9db73b9c9b9c81fe3693640aec83416a966c446afea54acfae3c"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:73a0dae8c71de3b0633a45c73f4a4a5ed09e94b43441d82981a781d4f12baa42"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a60290ec57e9b71767fba7c3645ddafdd0759974b540441510c629c6db6db24a"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:e5de0f6deada0dada870bb376a11bcd1f08abf3a968a6d118f33e72d1b1eb480"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:c799d49f1a5544a0ef7591c0ee75e0d6b93d6f56dc7a4979f59f7518d2872216"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:2baea1b0b989e5c152fe81425f7745ddc8901280ba3d97c98d8cdece7b706c60"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-win_amd64.whl", hash = "sha256:526345b3ed45f374f6317349df489167606736c876241ba984105afe7fd4839d"},
-    {file = "hf_xet-1.5.0-cp313-cp313t-win_arm64.whl", hash = "sha256:786d28e2eb8315d5035544b9d137b4a842d600c434bb91bf7d0d953cce906ad4"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:872d5601e6deea30d15865ede55d29eac6daf5a534ab417b99b6ef6b076dd96c"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:9929561f5abf4581c8ea79587881dfef6b8abb2a0d8a51915936fc2a614f4e73"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f7b7bbae318e583a86fb21e5a4a175d6721d628a2874f4bd022d0e660c32a682"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:cf7b2dc6f31a4ea754bb50f74cde482dcf5d366d184076d8530b9872787f3761"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:8dbcbab554c9ef158ef2c991545c3e970ddd8cc7acdcd0a78c5a41095dab4ded"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5906bf7718d3636dc13402914736abe723492cb730f744834f5f5b67d3a12702"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-win_amd64.whl", hash = "sha256:5f3dc2248fc01cc0a00cd392ab497f1ca373fcbc7e3f2da1f452480b384e839e"},
-    {file = "hf_xet-1.5.0-cp314-cp314t-win_arm64.whl", hash = "sha256:b285cea1b5bab46b758772716ba8d6854a1a0310fed1c249d678a8b38601e5a0"},
-    {file = "hf_xet-1.5.0-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:dad0dc84e941b8ba3c860659fe1fdc35c049d47cce293f003287757e971a8f56"},
-    {file = "hf_xet-1.5.0-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:fd6e5a9b0fdac4ed03ed45ef79254a655b1aaab514a02202617fbf643f5fdf7a"},
-    {file = "hf_xet-1.5.0-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3531b1823a0e6d77d80f9ed15ca0e00f0d115094f8ac033d5cae88f4564cc949"},
-    {file = "hf_xet-1.5.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:9a0ee58cd18d5ea799f7ed11290bbccbe56bdd8b1d97ca74b9cc49a3945d7a3b"},
-    {file = "hf_xet-1.5.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1e60df5a42e9bed8628b6416af2cba4cba57ae9f02de226a06b020d98e1aab18"},
-    {file = "hf_xet-1.5.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:4b35549ce62601b84da4ff9b24d970032ace3d4430f52d91bcbb26c901d6c690"},
-    {file = "hf_xet-1.5.0-cp37-abi3-win_amd64.whl", hash = "sha256:2806c7c17b4d23f8d88f7c4814f838c3b6150773fe339c20af23e1cfaf2797e4"},
-    {file = "hf_xet-1.5.0-cp37-abi3-win_arm64.whl", hash = "sha256:b6c9df403040248c76d808d3e047d64db2d923bae593eb244c41e425cf6cd7be"},
-    {file = "hf_xet-1.5.0.tar.gz", hash = "sha256:e0fb0a34d9f406eed88233e829a67ec016bec5af19e480eac65a233ea289a948"},
-]
-
-[package.extras]
-tests = ["pytest"]
-
 [[package]]
 name = "hpack"
 version = "4.1.0"
@ -1837,45 +1746,6 @@ files = [
    {file = "httpx_sse-0.4.3.tar.gz", hash = "sha256:9b1ed0127459a66014aec3c56bebd93da3c1bc8bb6618c8082039a44889a755d"},
 ]

-[[package]]
-name = "huggingface-hub"
-version = "0.36.2"
-description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
-optional = false
-python-versions = ">=3.8.0"
-groups = ["main"]
-files = [
-    {file = "huggingface_hub-0.36.2-py3-none-any.whl", hash = "sha256:48f0c8eac16145dfce371e9d2d7772854a4f591bcb56c9cf548accf531d54270"},
-    {file = "huggingface_hub-0.36.2.tar.gz", hash = "sha256:1934304d2fb224f8afa3b87007d58501acfda9215b334eed53072dd5e815ff7a"},
-]
-
-[package.dependencies]
-filelock = "*"
-fsspec = ">=2023.5.0"
-hf-xet = {version = ">=1.1.3,<2.0.0", markers = "platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\""}
-packaging = ">=20.9"
-pyyaml = ">=5.1"
-requests = "*"
-tqdm = ">=4.42.1"
-typing-extensions = ">=3.7.4.3"
-
-[package.extras]
-all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "ty", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
-cli = ["InquirerPy (==0.3.4)"]
-dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "ty", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
-fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
-hf-transfer = ["hf_transfer (>=0.1.4)"]
-hf-xet = ["hf-xet (>=1.1.2,<2.0.0)"]
-inference = ["aiohttp"]
-mcp = ["aiohttp", "mcp (>=1.8.0)", "typer"]
-oauth = ["authlib (>=1.3.2)", "fastapi", "httpx", "itsdangerous"]
-quality = ["libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "ruff (>=0.9.0)", "ty"]
-tensorflow = ["graphviz", "pydot", "tensorflow"]
-tensorflow-testing = ["keras (<3.0)", "tensorflow"]
-testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
-torch = ["safetensors[torch]", "torch"]
-typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
-
 [[package]]
 name = "hyperframe"
 version = "6.1.0"
@ -2076,18 +1946,6 @@ files = [
    {file = "jiter-0.14.0.tar.gz", hash = "sha256:e8a39e66dac7153cf3f964a12aad515afa8d74938ec5cc0018adcdae5367c79e"},
 ]

-[[package]]
-name = "joblib"
-version = "1.5.3"
-description = "Lightweight pipelining with Python functions"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "joblib-1.5.3-py3-none-any.whl", hash = "sha256:5fc3c5039fc5ca8c0276333a188bbd59d6b7ab37fe6632daa76bc7f9ec18e713"},
-    {file = "joblib-1.5.3.tar.gz", hash = "sha256:8561a3269e6801106863fd0d6d84bb737be9e7631e33aaed3fb9ce5953688da3"},
-]
-
 [[package]]
 name = "json-repair"
 version = "0.29.10"
@ -2893,24 +2751,6 @@ llms = ["google-genai (>=1.0.0)", "google-generativeai (>=0.3.0)", "groq (>=0.3.
 test = ["pytest (>=8.2.2)", "pytest-asyncio (>=0.23.7)", "pytest-mock (>=3.14.0)"]
 vector-stores = ["azure-search-documents (>=11.4.0b8)", "chromadb (>=0.4.24)", "faiss-cpu (>=1.7.4)", "pinecone (<=7.3.0)", "pinecone-text (>=0.10.0)", "pymochow (>=2.2.9)", "pymongo (>=4.13.2)", "upstash-vector (>=0.1.0)", "vecs (>=0.4.0)", "weaviate-client (>=4.4.0)"]

-[[package]]
-name = "mpmath"
-version = "1.3.0"
-description = "Python library for arbitrary-precision floating-point arithmetic"
-optional = false
-python-versions = "*"
-groups = ["main"]
-files = [
-    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
-    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
-]
-
-[package.extras]
-develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
-docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4) ; platform_python_implementation != \"PyPy\""]
-tests = ["pytest (>=4.6)"]
-
 [[package]]
 name = "multidict"
 version = "6.7.1"
@ -3067,54 +2907,6 @@ files = [
    {file = "multidict-6.7.1.tar.gz", hash = "sha256:ec6652a1bee61c53a3e5776b6049172c53b6aaba34f18c9ad04f82712bac623d"},
 ]

-[[package]]
-name = "networkx"
-version = "3.6"
-description = "Python package for creating and manipulating graphs and networks"
-optional = false
-python-versions = ">=3.11"
-groups = ["main"]
-markers = "python_version == \"3.14\""
-files = [
-    {file = "networkx-3.6-py3-none-any.whl", hash = "sha256:cdb395b105806062473d3be36458d8f1459a4e4b98e236a66c3a48996e07684f"},
-    {file = "networkx-3.6.tar.gz", hash = "sha256:285276002ad1f7f7da0f7b42f004bcba70d381e936559166363707fdad3d72ad"},
-]
-
-[package.extras]
-benchmarking = ["asv", "virtualenv"]
-default = ["matplotlib (>=3.8)", "numpy (>=1.25)", "pandas (>=2.0)", "scipy (>=1.11.2)"]
-developer = ["mypy (>=1.15)", "pre-commit (>=4.1)"]
-doc = ["intersphinx-registry", "myst-nb (>=1.1)", "numpydoc (>=1.8.0)", "pillow (>=10)", "pydata-sphinx-theme (>=0.16)", "sphinx (>=8.0)", "sphinx-gallery (>=0.18)", "texext (>=0.6.7)"]
-example = ["cairocffi (>=1.7)", "contextily (>=1.6)", "igraph (>=0.11)", "iplotx (>=0.9.0)", "momepy (>=0.7.2)", "osmnx (>=2.0.0)", "scikit-learn (>=1.5)", "seaborn (>=0.13)"]
-extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.10)"]
-release = ["build (>=0.10)", "changelist (==0.5)", "twine (>=4.0)", "wheel (>=0.40)"]
-test = ["pytest (>=7.2)", "pytest-cov (>=4.0)", "pytest-xdist (>=3.0)"]
-test-extras = ["pytest-mpl", "pytest-randomly"]
-
-[[package]]
-name = "networkx"
-version = "3.6.1"
-description = "Python package for creating and manipulating graphs and networks"
-optional = false
-python-versions = "!=3.14.1,>=3.11"
-groups = ["main"]
-markers = "python_version < \"3.14\""
-files = [
-    {file = "networkx-3.6.1-py3-none-any.whl", hash = "sha256:d47fbf302e7d9cbbb9e2555a0d267983d2aa476bac30e90dfbe5669bd57f3762"},
-    {file = "networkx-3.6.1.tar.gz", hash = "sha256:26b7c357accc0c8cde558ad486283728b65b6a95d85ee1cd66bafab4c8168509"},
-]
-
-[package.extras]
-benchmarking = ["asv", "virtualenv"]
-default = ["matplotlib (>=3.8)", "numpy (>=1.25)", "pandas (>=2.0)", "scipy (>=1.11.2)"]
-developer = ["mypy (>=1.15)", "pre-commit (>=4.1)"]
-doc = ["intersphinx-registry", "myst-nb (>=1.1)", "numpydoc (>=1.8.0)", "pillow (>=10)", "pydata-sphinx-theme (>=0.16)", "sphinx (>=8.0)", "sphinx-gallery (>=0.18)", "texext (>=0.6.7)"]
-example = ["cairocffi (>=1.7)", "contextily (>=1.6)", "igraph (>=0.11)", "iplotx (>=0.9.0)", "momepy (>=0.7.2)", "osmnx (>=2.0.0)", "scikit-learn (>=1.5)", "seaborn (>=0.13)"]
-extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.10)"]
-release = ["build (>=0.10)", "changelist (==0.5)", "twine (>=4.0)", "wheel (>=0.40)"]
-test = ["pytest (>=7.2)", "pytest-cov (>=4.0)", "pytest-xdist (>=3.0)"]
-test-extras = ["pytest-mpl", "pytest-randomly"]
-
 [[package]]
 name = "numpy"
 version = "1.26.4"
@ -3161,172 +2953,6 @@ files = [
    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
 ]

-[[package]]
-name = "nvidia-cublas-cu12"
-version = "12.1.3.1"
-description = "CUBLAS native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
-    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
-]
-
-[[package]]
-name = "nvidia-cuda-cupti-cu12"
-version = "12.1.105"
-description = "CUDA profiling tools runtime libs."
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
-    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
-]
-
-[[package]]
-name = "nvidia-cuda-nvrtc-cu12"
-version = "12.1.105"
-description = "NVRTC native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
-    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
-]
-
-[[package]]
-name = "nvidia-cuda-runtime-cu12"
-version = "12.1.105"
-description = "CUDA Runtime native Libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
-    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
-]
-
-[[package]]
-name = "nvidia-cudnn-cu12"
-version = "8.9.2.26"
-description = "cuDNN runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
-]
-
-[package.dependencies]
-nvidia-cublas-cu12 = "*"
-
-[[package]]
-name = "nvidia-cufft-cu12"
-version = "11.0.2.54"
-description = "CUFFT native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
-    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
-]
-
-[[package]]
-name = "nvidia-curand-cu12"
-version = "10.3.2.106"
-description = "CURAND native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
-    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
-]
-
-[[package]]
-name = "nvidia-cusolver-cu12"
-version = "11.4.5.107"
-description = "CUDA solver native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
-    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
-]
-
-[package.dependencies]
-nvidia-cublas-cu12 = "*"
-nvidia-cusparse-cu12 = "*"
-nvidia-nvjitlink-cu12 = "*"
-
-[[package]]
-name = "nvidia-cusparse-cu12"
-version = "12.1.0.106"
-description = "CUSPARSE native runtime libraries"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
-    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
-]
-
-[package.dependencies]
-nvidia-nvjitlink-cu12 = "*"
-
-[[package]]
-name = "nvidia-nccl-cu12"
-version = "2.19.3"
-description = "NVIDIA Collective Communication Library (NCCL) Runtime"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:a9734707a2c96443331c1e48c717024aa6678a0e2a4cb66b2c364d18cee6b48d"},
-]
-
-[[package]]
-name = "nvidia-nvjitlink-cu12"
-version = "12.9.86"
-description = "Nvidia JIT LTO Library"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:e3f1171dbdc83c5932a45f0f4c99180a70de9bd2718c1ab77d14104f6d7147f9"},
-    {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:994a05ef08ef4b0b299829cde613a424382aff7efb08a7172c1fa616cc3af2ca"},
-    {file = "nvidia_nvjitlink_cu12-12.9.86-py3-none-win_amd64.whl", hash = "sha256:cc6fcec260ca843c10e34c936921a1c426b351753587fdd638e8cff7b16bb9db"},
-]
-
-[[package]]
-name = "nvidia-nvtx-cu12"
-version = "12.1.105"
-description = "NVIDIA Tools Extension"
-optional = false
-python-versions = ">=3"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
-    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
-]
-
 [[package]]
 name = "obstore"
 version = "0.8.2"
@ -5353,222 +4979,6 @@ files = [
    {file = "rpds_py-0.30.0.tar.gz", hash = "sha256:dd8ff7cf90014af0c0f787eea34794ebf6415242ee1d6fa91eaba725cc441e84"},
 ]

-[[package]]
-name = "safetensors"
-version = "0.7.0"
-description = ""
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "safetensors-0.7.0-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:c82f4d474cf725255d9e6acf17252991c3c8aac038d6ef363a4bf8be2f6db517"},
-    {file = "safetensors-0.7.0-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:94fd4858284736bb67a897a41608b5b0c2496c9bdb3bf2af1fa3409127f20d57"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e07d91d0c92a31200f25351f4acb2bc6aff7f48094e13ebb1d0fb995b54b6542"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8469155f4cb518bafb4acf4865e8bb9d6804110d2d9bdcaa78564b9fd841e104"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:54bef08bf00a2bff599982f6b08e8770e09cc012d7bba00783fc7ea38f1fb37d"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:42cb091236206bb2016d245c377ed383aa7f78691748f3bb6ee1bfa51ae2ce6a"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dac7252938f0696ddea46f5e855dd3138444e82236e3be475f54929f0c510d48"},
-    {file = "safetensors-0.7.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1d060c70284127fa805085d8f10fbd0962792aed71879d00864acda69dbab981"},
-    {file = "safetensors-0.7.0-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:cdab83a366799fa730f90a4ebb563e494f28e9e92c4819e556152ad55e43591b"},
-    {file = "safetensors-0.7.0-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:672132907fcad9f2aedcb705b2d7b3b93354a2aec1b2f706c4db852abe338f85"},
-    {file = "safetensors-0.7.0-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:5d72abdb8a4d56d4020713724ba81dac065fedb7f3667151c4a637f1d3fb26c0"},
-    {file = "safetensors-0.7.0-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:b0f6d66c1c538d5a94a73aa9ddca8ccc4227e6c9ff555322ea40bdd142391dd4"},
-    {file = "safetensors-0.7.0-cp38-abi3-win32.whl", hash = "sha256:c74af94bf3ac15ac4d0f2a7c7b4663a15f8c2ab15ed0fc7531ca61d0835eccba"},
-    {file = "safetensors-0.7.0-cp38-abi3-win_amd64.whl", hash = "sha256:d1239932053f56f3456f32eb9625590cc7582e905021f94636202a864d470755"},
-    {file = "safetensors-0.7.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4729811a6640d019a4b7ba8638ee2fd21fa5ca8c7e7bdf0fed62068fcaac737"},
-    {file = "safetensors-0.7.0-pp310-pypy310_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:12f49080303fa6bb424b362149a12949dfbbf1e06811a88f2307276b0c131afd"},
-    {file = "safetensors-0.7.0-pp310-pypy310_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0071bffba4150c2f46cae1432d31995d77acfd9f8db598b5d1a2ce67e8440ad2"},
-    {file = "safetensors-0.7.0-pp310-pypy310_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:473b32699f4200e69801bf5abf93f1a4ecd432a70984df164fc22ccf39c4a6f3"},
-    {file = "safetensors-0.7.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b95a3fa7b3abb9b5b0e07668e808364d0d40f6bbbf9ae0faa8b5b210c97b140"},
-    {file = "safetensors-0.7.0-pp39-pypy39_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cfdead2f57330d76aa7234051dadfa7d4eedc0e5a27fd08e6f96714a92b00f09"},
-    {file = "safetensors-0.7.0-pp39-pypy39_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dc92bc2db7b45bda4510e4f51c59b00fe80b2d6be88928346e4294ce1c2abe7c"},
-    {file = "safetensors-0.7.0-pp39-pypy39_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6999421eb8ba9df4450a16d9184fcb7bef26240b9f98e95401f17af6c2210b71"},
-    {file = "safetensors-0.7.0.tar.gz", hash = "sha256:07663963b67e8bd9f0b8ad15bb9163606cd27cc5a1b96235a50d8369803b96b0"},
-]
-
-[package.extras]
-all = ["safetensors[jax]", "safetensors[numpy]", "safetensors[paddlepaddle]", "safetensors[pinned-tf]", "safetensors[quality]", "safetensors[testing]", "safetensors[torch]"]
-dev = ["safetensors[all]"]
-jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[numpy]"]
-mlx = ["mlx (>=0.0.9)"]
-numpy = ["numpy (>=1.21.6)"]
-paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"]
-pinned-tf = ["safetensors[numpy]", "tensorflow (==2.18.0)"]
-quality = ["ruff"]
-tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"]
-testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
-testingfree = ["huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
-torch = ["packaging", "safetensors[numpy]", "torch (>=1.10)"]
-
-[[package]]
-name = "scikit-learn"
-version = "1.8.0"
-description = "A set of python modules for machine learning and data mining"
-optional = false
-python-versions = ">=3.11"
-groups = ["main"]
-files = [
-    {file = "scikit_learn-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:146b4d36f800c013d267b29168813f7a03a43ecd2895d04861f1240b564421da"},
-    {file = "scikit_learn-1.8.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f984ca4b14914e6b4094c5d52a32ea16b49832c03bd17a110f004db3c223e8e1"},
-    {file = "scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5e30adb87f0cc81c7690a84f7932dd66be5bac57cfe16b91cb9151683a4a2d3b"},
-    {file = "scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ada8121bcb4dac28d930febc791a69f7cb1673c8495e5eee274190b73a4559c1"},
-    {file = "scikit_learn-1.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:c57b1b610bd1f40ba43970e11ce62821c2e6569e4d74023db19c6b26f246cb3b"},
-    {file = "scikit_learn-1.8.0-cp311-cp311-win_arm64.whl", hash = "sha256:2838551e011a64e3053ad7618dda9310175f7515f1742fa2d756f7c874c05961"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5fb63362b5a7ddab88e52b6dbb47dac3fd7dafeee740dc6c8d8a446ddedade8e"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:5025ce924beccb28298246e589c691fe1b8c1c96507e6d27d12c5fadd85bfd76"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4496bb2cf7a43ce1a2d7524a79e40bc5da45cf598dbf9545b7e8316ccba47bb4"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a0bcfe4d0d14aec44921545fd2af2338c7471de9cb701f1da4c9d85906ab847a"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:35c007dedb2ffe38fe3ee7d201ebac4a2deccd2408e8621d53067733e3c74809"},
-    {file = "scikit_learn-1.8.0-cp312-cp312-win_arm64.whl", hash = "sha256:8c497fff237d7b4e07e9ef1a640887fa4fb765647f86fbe00f969ff6280ce2bb"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0d6ae97234d5d7079dc0040990a6f7aeb97cb7fa7e8945f1999a429b23569e0a"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:edec98c5e7c128328124a029bceb09eda2d526997780fef8d65e9a69eead963e"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74b66d8689d52ed04c271e1329f0c61635bcaf5b926db9b12d58914cdc01fe57"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8fdf95767f989b0cfedb85f7ed8ca215d4be728031f56ff5a519ee1e3276dc2e"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-win_amd64.whl", hash = "sha256:2de443b9373b3b615aec1bb57f9baa6bb3a9bd093f1269ba95c17d870422b271"},
-    {file = "scikit_learn-1.8.0-cp313-cp313-win_arm64.whl", hash = "sha256:eddde82a035681427cbedded4e6eff5e57fa59216c2e3e90b10b19ab1d0a65c3"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:7cc267b6108f0a1499a734167282c00c4ebf61328566b55ef262d48e9849c735"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:fe1c011a640a9f0791146011dfd3c7d9669785f9fed2b2a5f9e207536cf5c2fd"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:72358cce49465d140cc4e7792015bb1f0296a9742d5622c67e31399b75468b9e"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:80832434a6cc114f5219211eec13dcbc16c2bac0e31ef64c6d346cde3cf054cb"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-win_amd64.whl", hash = "sha256:ee787491dbfe082d9c3013f01f5991658b0f38aa8177e4cd4bf434c58f551702"},
-    {file = "scikit_learn-1.8.0-cp313-cp313t-win_arm64.whl", hash = "sha256:bf97c10a3f5a7543f9b88cbf488d33d175e9146115a451ae34568597ba33dcde"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c22a2da7a198c28dd1a6e1136f19c830beab7fdca5b3e5c8bba8394f8a5c45b3"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:6b595b07a03069a2b1740dc08c2299993850ea81cce4fe19b2421e0c970de6b7"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:29ffc74089f3d5e87dfca4c2c8450f88bdc61b0fc6ed5d267f3988f19a1309f6"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb65db5d7531bccf3a4f6bec3462223bea71384e2cda41da0f10b7c292b9e7c4"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-win_amd64.whl", hash = "sha256:56079a99c20d230e873ea40753102102734c5953366972a71d5cb39a32bc40c6"},
-    {file = "scikit_learn-1.8.0-cp314-cp314-win_arm64.whl", hash = "sha256:3bad7565bc9cf37ce19a7c0d107742b320c1285df7aab1a6e2d28780df167242"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:4511be56637e46c25721e83d1a9cea9614e7badc7040c4d573d75fbe257d6fd7"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:a69525355a641bf8ef136a7fa447672fb54fe8d60cab5538d9eb7c6438543fb9"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c2656924ec73e5939c76ac4c8b026fc203b83d8900362eb2599d8aee80e4880f"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15fc3b5d19cc2be65404786857f2e13c70c83dd4782676dd6814e3b89dc8f5b9"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-win_amd64.whl", hash = "sha256:00d6f1d66fbcf4eba6e356e1420d33cc06c70a45bb1363cd6f6a8e4ebbbdece2"},
-    {file = "scikit_learn-1.8.0-cp314-cp314t-win_arm64.whl", hash = "sha256:f28dd15c6bb0b66ba09728cf09fd8736c304be29409bd8445a080c1280619e8c"},
-    {file = "scikit_learn-1.8.0.tar.gz", hash = "sha256:9bccbb3b40e3de10351f8f5068e105d0f4083b1a65fa07b6634fbc401a6287fd"},
-]
-
-[package.dependencies]
-joblib = ">=1.3.0"
-numpy = ">=1.24.1"
-scipy = ">=1.10.0"
-threadpoolctl = ">=3.2.0"
-
-[package.extras]
-benchmark = ["matplotlib (>=3.6.1)", "memory_profiler (>=0.57.0)", "pandas (>=1.5.0)"]
-build = ["cython (>=3.1.2)", "meson-python (>=0.17.1)", "numpy (>=1.24.1)", "scipy (>=1.10.0)"]
-docs = ["Pillow (>=10.1.0)", "matplotlib (>=3.6.1)", "memory_profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.5.0)", "plotly (>=5.18.0)", "polars (>=0.20.30)", "pooch (>=1.8.0)", "pydata-sphinx-theme (>=0.15.3)", "scikit-image (>=0.22.0)", "seaborn (>=0.13.0)", "sphinx (>=7.3.7)", "sphinx-copybutton (>=0.5.2)", "sphinx-design (>=0.6.0)", "sphinx-gallery (>=0.17.1)", "sphinx-prompt (>=1.4.0)", "sphinx-remove-toctrees (>=1.0.0.post1)", "sphinxcontrib-sass (>=0.3.4)", "sphinxext-opengraph (>=0.9.1)", "towncrier (>=24.8.0)"]
-examples = ["matplotlib (>=3.6.1)", "pandas (>=1.5.0)", "plotly (>=5.18.0)", "pooch (>=1.8.0)", "scikit-image (>=0.22.0)", "seaborn (>=0.13.0)"]
-install = ["joblib (>=1.3.0)", "numpy (>=1.24.1)", "scipy (>=1.10.0)", "threadpoolctl (>=3.2.0)"]
-maintenance = ["conda-lock (==3.0.1)"]
-tests = ["matplotlib (>=3.6.1)", "mypy (>=1.15)", "numpydoc (>=1.2.0)", "pandas (>=1.5.0)", "polars (>=0.20.30)", "pooch (>=1.8.0)", "pyamg (>=5.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.11.7)"]
-
-[[package]]
-name = "scipy"
-version = "1.17.1"
-description = "Fundamental algorithms for scientific computing in Python"
-optional = false
-python-versions = ">=3.11"
-groups = ["main"]
-files = [
-    {file = "scipy-1.17.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:1f95b894f13729334fb990162e911c9e5dc1ab390c58aa6cbecb389c5b5e28ec"},
-    {file = "scipy-1.17.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:e18f12c6b0bc5a592ed23d3f7b891f68fd7f8241d69b7883769eb5d5dfb52696"},
-    {file = "scipy-1.17.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:a3472cfbca0a54177d0faa68f697d8ba4c80bbdc19908c3465556d9f7efce9ee"},
-    {file = "scipy-1.17.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:766e0dc5a616d026a3a1cffa379af959671729083882f50307e18175797b3dfd"},
-    {file = "scipy-1.17.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:744b2bf3640d907b79f3fd7874efe432d1cf171ee721243e350f55234b4cec4c"},
-    {file = "scipy-1.17.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:43af8d1f3bea642559019edfe64e9b11192a8978efbd1539d7bc2aaa23d92de4"},
-    {file = "scipy-1.17.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:cd96a1898c0a47be4520327e01f874acfd61fb48a9420f8aa9f6483412ffa444"},
-    {file = "scipy-1.17.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4eb6c25dd62ee8d5edf68a8e1c171dd71c292fdae95d8aeb3dd7d7de4c364082"},
-    {file = "scipy-1.17.1-cp311-cp311-win_amd64.whl", hash = "sha256:d30e57c72013c2a4fe441c2fcb8e77b14e152ad48b5464858e07e2ad9fbfceff"},
-    {file = "scipy-1.17.1-cp311-cp311-win_arm64.whl", hash = "sha256:9ecb4efb1cd6e8c4afea0daa91a87fbddbce1b99d2895d151596716c0b2e859d"},
-    {file = "scipy-1.17.1-cp312-cp312-macosx_10_14_x86_64.whl", hash = "sha256:35c3a56d2ef83efc372eaec584314bd0ef2e2f0d2adb21c55e6ad5b344c0dcb8"},
-    {file = "scipy-1.17.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:fcb310ddb270a06114bb64bbe53c94926b943f5b7f0842194d585c65eb4edd76"},
-    {file = "scipy-1.17.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:cc90d2e9c7e5c7f1a482c9875007c095c3194b1cfedca3c2f3291cdc2bc7c086"},
-    {file = "scipy-1.17.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:c80be5ede8f3f8eded4eff73cc99a25c388ce98e555b17d31da05287015ffa5b"},
-    {file = "scipy-1.17.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e19ebea31758fac5893a2ac360fedd00116cbb7628e650842a6691ba7ca28a21"},
-    {file = "scipy-1.17.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:02ae3b274fde71c5e92ac4d54bc06c42d80e399fec704383dcd99b301df37458"},
-    {file = "scipy-1.17.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8a604bae87c6195d8b1045eddece0514d041604b14f2727bbc2b3020172045eb"},
-    {file = "scipy-1.17.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f590cd684941912d10becc07325a3eeb77886fe981415660d9265c4c418d0bea"},
-    {file = "scipy-1.17.1-cp312-cp312-win_amd64.whl", hash = "sha256:41b71f4a3a4cab9d366cd9065b288efc4d4f3c0b37a91a8e0947fb5bd7f31d87"},
-    {file = "scipy-1.17.1-cp312-cp312-win_arm64.whl", hash = "sha256:f4115102802df98b2b0db3cce5cb9b92572633a1197c77b7553e5203f284a5b3"},
-    {file = "scipy-1.17.1-cp313-cp313-macosx_10_14_x86_64.whl", hash = "sha256:5e3c5c011904115f88a39308379c17f91546f77c1667cea98739fe0fccea804c"},
-    {file = "scipy-1.17.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:6fac755ca3d2c3edcb22f479fceaa241704111414831ddd3bc6056e18516892f"},
-    {file = "scipy-1.17.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:7ff200bf9d24f2e4d5dc6ee8c3ac64d739d3a89e2326ba68aaf6c4a2b838fd7d"},
-    {file = "scipy-1.17.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:4b400bdc6f79fa02a4d86640310dde87a21fba0c979efff5248908c6f15fad1b"},
-    {file = "scipy-1.17.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2b64ca7d4aee0102a97f3ba22124052b4bd2152522355073580bf4845e2550b6"},
-    {file = "scipy-1.17.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:581b2264fc0aa555f3f435a5944da7504ea3a065d7029ad60e7c3d1ae09c5464"},
-    {file = "scipy-1.17.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:beeda3d4ae615106d7094f7e7cef6218392e4465cc95d25f900bebabfded0950"},
-    {file = "scipy-1.17.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6609bc224e9568f65064cfa72edc0f24ee6655b47575954ec6339534b2798369"},
-    {file = "scipy-1.17.1-cp313-cp313-win_amd64.whl", hash = "sha256:37425bc9175607b0268f493d79a292c39f9d001a357bebb6b88fdfaff13f6448"},
-    {file = "scipy-1.17.1-cp313-cp313-win_arm64.whl", hash = "sha256:5cf36e801231b6a2059bf354720274b7558746f3b1a4efb43fcf557ccd484a87"},
-    {file = "scipy-1.17.1-cp313-cp313t-macosx_10_14_x86_64.whl", hash = "sha256:d59c30000a16d8edc7e64152e30220bfbd724c9bbb08368c054e24c651314f0a"},
-    {file = "scipy-1.17.1-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:010f4333c96c9bb1a4516269e33cb5917b08ef2166d5556ca2fd9f082a9e6ea0"},
-    {file = "scipy-1.17.1-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:2ceb2d3e01c5f1d83c4189737a42d9cb2fc38a6eeed225e7515eef71ad301dce"},
-    {file = "scipy-1.17.1-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:844e165636711ef41f80b4103ed234181646b98a53c8f05da12ca5ca289134f6"},
-    {file = "scipy-1.17.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:158dd96d2207e21c966063e1635b1063cd7787b627b6f07305315dd73d9c679e"},
-    {file = "scipy-1.17.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:74cbb80d93260fe2ffa334efa24cb8f2f0f622a9b9febf8b483c0b865bfb3475"},
-    {file = "scipy-1.17.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:dbc12c9f3d185f5c737d801da555fb74b3dcfa1a50b66a1a93e09190f41fab50"},
-    {file = "scipy-1.17.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:94055a11dfebe37c656e70317e1996dc197e1a15bbcc351bcdd4610e128fe1ca"},
-    {file = "scipy-1.17.1-cp313-cp313t-win_amd64.whl", hash = "sha256:e30bdeaa5deed6bc27b4cc490823cd0347d7dae09119b8803ae576ea0ce52e4c"},
-    {file = "scipy-1.17.1-cp313-cp313t-win_arm64.whl", hash = "sha256:a720477885a9d2411f94a93d16f9d89bad0f28ca23c3f8daa521e2dcc3f44d49"},
-    {file = "scipy-1.17.1-cp314-cp314-macosx_10_14_x86_64.whl", hash = "sha256:a48a72c77a310327f6a3a920092fa2b8fd03d7deaa60f093038f22d98e096717"},
-    {file = "scipy-1.17.1-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:45abad819184f07240d8a696117a7aacd39787af9e0b719d00285549ed19a1e9"},
-    {file = "scipy-1.17.1-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:3fd1fcdab3ea951b610dc4cef356d416d5802991e7e32b5254828d342f7b7e0b"},
-    {file = "scipy-1.17.1-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:7bdf2da170b67fdf10bca777614b1c7d96ae3ca5794fd9587dce41eb2966e866"},
-    {file = "scipy-1.17.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:adb2642e060a6549c343603a3851ba76ef0b74cc8c079a9a58121c7ec9fe2350"},
-    {file = "scipy-1.17.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:eee2cfda04c00a857206a4330f0c5e3e56535494e30ca445eb19ec624ae75118"},
-    {file = "scipy-1.17.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:d2650c1fb97e184d12d8ba010493ee7b322864f7d3d00d3f9bb97d9c21de4068"},
-    {file = "scipy-1.17.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:08b900519463543aa604a06bec02461558a6e1cef8fdbb8098f77a48a83c8118"},
-    {file = "scipy-1.17.1-cp314-cp314-win_amd64.whl", hash = "sha256:3877ac408e14da24a6196de0ddcace62092bfc12a83823e92e49e40747e52c19"},
-    {file = "scipy-1.17.1-cp314-cp314-win_arm64.whl", hash = "sha256:f8885db0bc2bffa59d5c1b72fad7a6a92d3e80e7257f967dd81abb553a90d293"},
-    {file = "scipy-1.17.1-cp314-cp314t-macosx_10_14_x86_64.whl", hash = "sha256:1cc682cea2ae55524432f3cdff9e9a3be743d52a7443d0cba9017c23c87ae2f6"},
-    {file = "scipy-1.17.1-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:2040ad4d1795a0ae89bfc7e8429677f365d45aa9fd5e4587cf1ea737f927b4a1"},
-    {file = "scipy-1.17.1-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:131f5aaea57602008f9822e2115029b55d4b5f7c070287699fe45c661d051e39"},
-    {file = "scipy-1.17.1-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:9cdc1a2fcfd5c52cfb3045feb399f7b3ce822abdde3a193a6b9a60b3cb5854ca"},
-    {file = "scipy-1.17.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e3dcd57ab780c741fde8dc68619de988b966db759a3c3152e8e9142c26295ad"},
-    {file = "scipy-1.17.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a9956e4d4f4a301ebf6cde39850333a6b6110799d470dbbb1e25326ac447f52a"},
-    {file = "scipy-1.17.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:a4328d245944d09fd639771de275701ccadf5f781ba0ff092ad141e017eccda4"},
-    {file = "scipy-1.17.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:a77cbd07b940d326d39a1d1b37817e2ee4d79cb30e7338f3d0cddffae70fcaa2"},
-    {file = "scipy-1.17.1-cp314-cp314t-win_amd64.whl", hash = "sha256:eb092099205ef62cd1782b006658db09e2fed75bffcae7cc0d44052d8aa0f484"},
-    {file = "scipy-1.17.1-cp314-cp314t-win_arm64.whl", hash = "sha256:200e1050faffacc162be6a486a984a0497866ec54149a01270adc8a59b7c7d21"},
-    {file = "scipy-1.17.1.tar.gz", hash = "sha256:95d8e012d8cb8816c226aef832200b1d45109ed4464303e997c5b13122b297c0"},
-]
-
-[package.dependencies]
-numpy = ">=1.26.4,<2.7"
-
-[package.extras]
-dev = ["click (<8.3.0)", "cython-lint (>=0.12.2)", "mypy (==1.10.0)", "pycodestyle", "ruff (>=0.12.0)", "spin", "types-psutil", "typing_extensions"]
-doc = ["intersphinx_registry", "jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.19.1)", "jupytext", "linkify-it-py", "matplotlib (>=3.5)", "myst-nb (>=1.2.0)", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0,<8.2.0)", "sphinx-copybutton", "sphinx-design (>=0.4.0)", "tabulate"]
-test = ["Cython", "array-api-strict (>=2.3.1)", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja ; sys_platform != \"emscripten\"", "pooch", "pytest (>=8.0.0)", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
-
-[[package]]
-name = "sentence-transformers"
-version = "3.4.1"
-description = "State-of-the-Art Text Embeddings"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "sentence_transformers-3.4.1-py3-none-any.whl", hash = "sha256:e026dc6d56801fd83f74ad29a30263f401b4b522165c19386d8bc10dcca805da"},
-    {file = "sentence_transformers-3.4.1.tar.gz", hash = "sha256:68daa57504ff548340e54ff117bd86c1d2f784b21e0fb2689cf3272b8937b24b"},
-]
-
-[package.dependencies]
-huggingface-hub = ">=0.20.0"
-Pillow = "*"
-scikit-learn = "*"
-scipy = "*"
-torch = ">=1.11.0"
-tqdm = "*"
-transformers = ">=4.41.0,<5.0.0"
-
-[package.extras]
-dev = ["accelerate (>=0.20.3)", "datasets", "peft", "pre-commit", "pytest", "pytest-cov"]
-onnx = ["optimum[onnxruntime] (>=1.23.1)"]
-onnx-gpu = ["optimum[onnxruntime-gpu] (>=1.23.1)"]
-openvino = ["optimum-intel[openvino] (>=1.20.0)"]
-train = ["accelerate (>=0.20.3)", "datasets"]
-
 [[package]]
 name = "setuptools"
 version = "70.3.0"
@ -5789,24 +5199,6 @@ files = [
    {file = "structlog-25.5.0.tar.gz", hash = "sha256:098522a3bebed9153d4570c6d0288abf80a031dfdb2048d59a49e9dc2190fc98"},
 ]

-[[package]]
-name = "sympy"
-version = "1.14.0"
-description = "Computer algebra system (CAS) in Python"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5"},
-    {file = "sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517"},
-]
-
-[package.dependencies]
-mpmath = ">=1.1.0,<1.4"
-
-[package.extras]
-dev = ["hypothesis (>=6.70.0)", "pytest (>=7.1.0)"]
-
 [[package]]
 name = "tavily-python"
 version = "0.7.24"
@ -5990,18 +5382,6 @@ files = [
    {file = "textual_speedups-0.2.1.tar.gz", hash = "sha256:72cf0f7bdeede015367b59b70bcf724ba2c3080a8641ebc5eb94b36ad1536824"},
 ]

-[[package]]
-name = "threadpoolctl"
-version = "3.6.0"
-description = "threadpoolctl"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb"},
-    {file = "threadpoolctl-3.6.0.tar.gz", hash = "sha256:8ab8b4aa3491d812b623328249fab5302a68d2d71745c8a4c719a2fcaba9f44e"},
-]
-
 [[package]]
 name = "tiktoken"
 version = "0.13.0"
@ -6076,48 +5456,6 @@ requests = "*"
 [package.extras]
 blobfile = ["blobfile (>=3)"]

-[[package]]
-name = "tokenizers"
-version = "0.22.2"
-description = ""
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "tokenizers-0.22.2-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:544dd704ae7238755d790de45ba8da072e9af3eea688f698b137915ae959281c"},
-    {file = "tokenizers-0.22.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1e418a55456beedca4621dbab65a318981467a2b188e982a23e117f115ce5001"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2249487018adec45d6e3554c71d46eb39fa8ea67156c640f7513eb26f318cec7"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:25b85325d0815e86e0bac263506dd114578953b7b53d7de09a6485e4a160a7dd"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bfb88f22a209ff7b40a576d5324bf8286b519d7358663db21d6246fb17eea2d5"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1c774b1276f71e1ef716e5486f21e76333464f47bece56bbd554485982a9e03e"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:df6c4265b289083bf710dff49bc51ef252f9d5be33a45ee2bed151114a56207b"},
-    {file = "tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:369cc9fc8cc10cb24143873a0d95438bb8ee257bb80c71989e3ee290e8d72c67"},
-    {file = "tokenizers-0.22.2-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:29c30b83d8dcd061078b05ae0cb94d3c710555fbb44861139f9f83dcca3dc3e4"},
-    {file = "tokenizers-0.22.2-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:37ae80a28c1d3265bb1f22464c856bd23c02a05bb211e56d0c5301a435be6c1a"},
-    {file = "tokenizers-0.22.2-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:791135ee325f2336f498590eb2f11dc5c295232f288e75c99a36c5dbce63088a"},
-    {file = "tokenizers-0.22.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:38337540fbbddff8e999d59970f3c6f35a82de10053206a7562f1ea02d046fa5"},
-    {file = "tokenizers-0.22.2-cp39-abi3-win32.whl", hash = "sha256:a6bf3f88c554a2b653af81f3204491c818ae2ac6fbc09e76ef4773351292bc92"},
-    {file = "tokenizers-0.22.2-cp39-abi3-win_amd64.whl", hash = "sha256:c9ea31edff2968b44a88f97d784c2f16dc0729b8b143ed004699ebca91f05c48"},
-    {file = "tokenizers-0.22.2-cp39-abi3-win_arm64.whl", hash = "sha256:9ce725d22864a1e965217204946f830c37876eee3b2ba6fc6255e8e903d5fcbc"},
-    {file = "tokenizers-0.22.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:753d47ebd4542742ef9261d9da92cd545b2cacbb48349a1225466745bb866ec4"},
-    {file = "tokenizers-0.22.2-pp310-pypy310_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e10bf9113d209be7cd046d40fbabbaf3278ff6d18eb4da4c500443185dc1896c"},
-    {file = "tokenizers-0.22.2-pp310-pypy310_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:64d94e84f6660764e64e7e0b22baa72f6cd942279fdbb21d46abd70d179f0195"},
-    {file = "tokenizers-0.22.2-pp310-pypy310_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f01a9c019878532f98927d2bacb79bbb404b43d3437455522a00a30718cdedb5"},
-    {file = "tokenizers-0.22.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:319f659ee992222f04e58f84cbf407cfa66a65fe3a8de44e8ad2bc53e7d99012"},
-    {file = "tokenizers-0.22.2-pp39-pypy39_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1e50f8554d504f617d9e9d6e4c2c2884a12b388a97c5c77f0bc6cf4cd032feee"},
-    {file = "tokenizers-0.22.2-pp39-pypy39_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1a62ba2c5faa2dd175aaeed7b15abf18d20266189fb3406c5d0550dd34dd5f37"},
-    {file = "tokenizers-0.22.2-pp39-pypy39_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:143b999bdc46d10febb15cbffb4207ddd1f410e2c755857b5a0797961bbdc113"},
-    {file = "tokenizers-0.22.2.tar.gz", hash = "sha256:473b83b915e547aa366d1eee11806deaf419e17be16310ac0a14077f1e28f917"},
-]
-
-[package.dependencies]
-huggingface-hub = ">=0.16.4,<2.0"
-
-[package.extras]
-dev = ["tokenizers[testing]"]
-docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
-testing = ["datasets", "numpy", "pytest", "pytest-asyncio", "requests", "ruff", "ty"]
-
 [[package]]
 name = "toml"
 version = "0.10.2"
@ -6142,65 +5480,6 @@ files = [
    {file = "tomli_w-1.2.0.tar.gz", hash = "sha256:2dd14fac5a47c27be9cd4c976af5a12d87fb1f0b4512f81d69cce3b35ae25021"},
 ]

-[[package]]
-name = "torch"
-version = "2.2.0"
-description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
-optional = false
-python-versions = ">=3.8.0"
-groups = ["main"]
-files = [
-    {file = "torch-2.2.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:d366158d6503a3447e67f8c0ad1328d54e6c181d88572d688a625fac61b13a97"},
-    {file = "torch-2.2.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:707f2f80402981e9f90d0038d7d481678586251e6642a7a6ef67fc93511cb446"},
-    {file = "torch-2.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:15c8f0a105c66b28496092fca1520346082e734095f8eaf47b5786bac24b8a31"},
-    {file = "torch-2.2.0-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:0ca4df4b728515ad009b79f5107b00bcb2c63dc202d991412b9eb3b6a4f24349"},
-    {file = "torch-2.2.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:3d3eea2d5969b9a1c9401429ca79efc668120314d443d3463edc3289d7f003c7"},
-    {file = "torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:0d1c580e379c0d48f0f0a08ea28d8e373295aa254de4f9ad0631f9ed8bc04c24"},
-    {file = "torch-2.2.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:9328e3c1ce628a281d2707526b4d1080eae7c4afab4f81cea75bde1f9441dc78"},
-    {file = "torch-2.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:03c8e660907ac1b8ee07f6d929c4e15cd95be2fb764368799cca02c725a212b8"},
-    {file = "torch-2.2.0-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:da0cefe7f84ece3e3b56c11c773b59d1cb2c0fd83ddf6b5f7f1fd1a987b15c3e"},
-    {file = "torch-2.2.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:f81d23227034221a4a4ff8ef24cc6cec7901edd98d9e64e32822778ff01be85e"},
-    {file = "torch-2.2.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:dcbfb2192ac41ca93c756ebe9e2af29df0a4c14ee0e7a0dd78f82c67a63d91d4"},
-    {file = "torch-2.2.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:9eeb42971619e24392c9088b5b6d387d896e267889d41d267b1fec334f5227c5"},
-    {file = "torch-2.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:c718b2ca69a6cac28baa36d86d8c0ec708b102cebd1ceb1b6488e404cd9be1d1"},
-    {file = "torch-2.2.0-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:f11d18fceb4f9ecb1ac680dde7c463c120ed29056225d75469c19637e9f98d12"},
-    {file = "torch-2.2.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:ee1da852bfd4a7e674135a446d6074c2da7194c1b08549e31eae0b3138c6b4d2"},
-    {file = "torch-2.2.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:0d819399819d0862268ac531cf12a501c253007df4f9e6709ede8a0148f1a7b8"},
-    {file = "torch-2.2.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:08f53ccc38c49d839bc703ea1b20769cc8a429e0c4b20b56921a9f64949bf325"},
-    {file = "torch-2.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:93bffe3779965a71dab25fc29787538c37c5d54298fd2f2369e372b6fb137d41"},
-    {file = "torch-2.2.0-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:c17ec323da778efe8dad49d8fb534381479ca37af1bfc58efdbb8607a9d263a3"},
-    {file = "torch-2.2.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:c02685118008834e878f676f81eab3a952b7936fa31f474ef8a5ff4b5c78b36d"},
-    {file = "torch-2.2.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:d9f39d6f53cec240a0e3baa82cb697593340f9d4554cee6d3d6ca07925c2fac0"},
-    {file = "torch-2.2.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:51770c065206250dc1222ea7c0eff3f88ab317d3e931cca2aee461b85fbc2472"},
-    {file = "torch-2.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:008e4c6ad703de55af760c73bf937ecdd61a109f9b08f2bbb9c17e7c7017f194"},
-    {file = "torch-2.2.0-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:de8680472dd14e316f42ceef2a18a301461a9058cd6e99a1f1b20f78f11412f1"},
-    {file = "torch-2.2.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:99e1dcecb488e3fd25bcaac56e48cdb3539842904bdc8588b0b255fde03a254c"},
-]
-
-[package.dependencies]
-filelock = "*"
-fsspec = "*"
-jinja2 = "*"
-networkx = "*"
-nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-nccl-cu12 = {version = "2.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-sympy = "*"
-triton = {version = "2.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
-typing-extensions = ">=4.8.0"
-
-[package.extras]
-opt-einsum = ["opt-einsum (>=3.3)"]
-optree = ["optree (>=0.9.1)"]
-
 [[package]]
 name = "tqdm"
 version = "4.67.3"
@ -6223,106 +5502,6 @@ notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
 telegram = ["requests"]

-[[package]]
-name = "transformers"
-version = "4.57.6"
-description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
-optional = false
-python-versions = ">=3.9.0"
-groups = ["main"]
-files = [
-    {file = "transformers-4.57.6-py3-none-any.whl", hash = "sha256:4c9e9de11333ddfe5114bc872c9f370509198acf0b87a832a0ab9458e2bd0550"},
-    {file = "transformers-4.57.6.tar.gz", hash = "sha256:55e44126ece9dc0a291521b7e5492b572e6ef2766338a610b9ab5afbb70689d3"},
-]
-
-[package.dependencies]
-filelock = "*"
-huggingface-hub = ">=0.34.0,<1.0"
-numpy = ">=1.17"
-packaging = ">=20.0"
-pyyaml = ">=5.1"
-regex = "!=2019.12.17"
-requests = "*"
-safetensors = ">=0.4.3"
-tokenizers = ">=0.22.0,<=0.23.0"
-tqdm = ">=4.27"
-
-[package.extras]
-accelerate = ["accelerate (>=0.26.0)"]
-all = ["Pillow (>=10.0.1,<=15.0)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "accelerate (>=0.26.0)", "av", "codecarbon (>=2.8.1)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "jinja2 (>=3.1.0)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "kernels (>=0.6.1,<=0.9)", "librosa", "mistral-common[opencv] (>=1.6.3)", "num2words", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "torchaudio", "torchvision"]
-audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
-benchmark = ["optimum-benchmark (>=0.3.0)"]
-chat-template = ["jinja2 (>=3.1.0)"]
-codecarbon = ["codecarbon (>=2.8.1)"]
-deepspeed = ["accelerate (>=0.26.0)", "deepspeed (>=0.9.3)"]
-deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.26.0)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fastapi", "libcst", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "openai (>=1.98.0)", "optuna", "parameterized (>=0.9)", "protobuf", "psutil", "pydantic (>=2)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures (<16.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.13.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "sentencepiece (>=0.1.91,!=0.1.92)", "starlette", "tensorboard", "timeout-decorator", "torch (>=2.2)", "uvicorn"]
-dev = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "accelerate (>=0.26.0)", "accelerate (>=0.26.0)", "av", "beautifulsoup4", "codecarbon (>=2.8.1)", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fastapi", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "jinja2 (>=3.1.0)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "kernels (>=0.6.1,<=0.9)", "libcst", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "num2words", "onnxconverter-common", "openai (>=1.98.0)", "optax (>=0.0.8,<=0.1.4)", "optuna", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures (<16.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.13.1)", "ruff (==0.13.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sentencepiece (>=0.1.91,!=0.1.92)", "starlette", "sudachidict_core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "torch (>=2.2)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic_lite (>=1.0.7)", "urllib3 (<2.0.0)", "uvicorn"]
-dev-tensorflow = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fastapi", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "libcst", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "onnxconverter-common", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "openai (>=1.98.0)", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures (<16.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.13.1)", "ruff (==0.13.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sentencepiece (>=0.1.91,!=0.1.92)", "starlette", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "tf2onnx", "timeout-decorator", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "urllib3 (<2.0.0)", "uvicorn"]
-dev-torch = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "accelerate (>=0.26.0)", "beautifulsoup4", "codecarbon (>=2.8.1)", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fastapi", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "kenlm", "kernels (>=0.6.1,<=0.9)", "libcst", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "num2words", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "openai (>=1.98.0)", "optuna", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures (<16.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.13.1)", "ruff (==0.13.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sentencepiece (>=0.1.91,!=0.1.92)", "starlette", "sudachidict_core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "torch (>=2.2)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic_lite (>=1.0.7)", "urllib3 (<2.0.0)", "uvicorn"]
-flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"]
-flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
-ftfy = ["ftfy"]
-hf-xet = ["hf_xet"]
-hub-kernels = ["kernels (>=0.6.1,<=0.9)"]
-integrations = ["kernels (>=0.6.1,<=0.9)", "optuna", "ray[tune] (>=2.7.0)"]
-ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict_core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic_lite (>=1.0.7)"]
-mistral-common = ["mistral-common[opencv] (>=1.6.3)"]
-modelcreation = ["cookiecutter (==1.7.3)"]
-natten = ["natten (>=0.14.6,<0.15.0)"]
-num2words = ["num2words"]
-onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
-onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
-open-telemetry = ["opentelemetry-api", "opentelemetry-exporter-otlp", "opentelemetry-sdk"]
-optuna = ["optuna"]
-quality = ["GitPython (<3.1.19)", "datasets (>=2.15.0)", "libcst", "pandas (<2.3.0)", "rich", "ruff (==0.13.1)", "urllib3 (<2.0.0)"]
-ray = ["ray[tune] (>=2.7.0)"]
-retrieval = ["datasets (>=2.15.0)", "faiss-cpu"]
-ruff = ["ruff (==0.13.1)"]
-sagemaker = ["sagemaker (>=2.31.0)"]
-sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"]
-serving = ["accelerate (>=0.26.0)", "fastapi", "openai (>=1.98.0)", "pydantic (>=2)", "starlette", "torch (>=2.2)", "uvicorn"]
-sigopt = ["sigopt"]
-sklearn = ["scikit-learn"]
-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
-testing = ["GitPython (<3.1.19)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fastapi", "libcst", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "openai (>=1.98.0)", "parameterized (>=0.9)", "psutil", "pydantic (>=2)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures (<16.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.13.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "starlette", "tensorboard", "timeout-decorator", "torch (>=2.2)", "uvicorn"]
-tf = ["keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
-tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<0.24)", "tensorflow-text (<2.16)", "tf2onnx"]
-tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
-tiktoken = ["blobfile", "tiktoken"]
-timm = ["timm (!=1.0.18,<=1.0.19)"]
-tokenizers = ["tokenizers (>=0.22.0,<=0.23.0)"]
-torch = ["accelerate (>=0.26.0)", "torch (>=2.2)"]
-torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
-torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"]
-torchhub = ["filelock", "huggingface-hub (>=0.34.0,<1.0)", "importlib_metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "tqdm (>=4.27)"]
-video = ["av"]
-vision = ["Pillow (>=10.0.1,<=15.0)"]
-
-[[package]]
-name = "triton"
-version = "2.2.0"
-description = "A language and compiler for custom Deep Learning operations"
-optional = false
-python-versions = "*"
-groups = ["main"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
-files = [
-    {file = "triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2294514340cfe4e8f4f9e5c66c702744c4a117d25e618bd08469d0bfed1e2e5"},
-    {file = "triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da58a152bddb62cafa9a857dd2bc1f886dbf9f9c90a2b5da82157cd2b34392b0"},
-    {file = "triton-2.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0af58716e721460a61886668b205963dc4d1e4ac20508cc3f623aef0d70283d5"},
-    {file = "triton-2.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8fe46d3ab94a8103e291bd44c741cc294b91d1d81c1a2888254cbf7ff846dab"},
-    {file = "triton-2.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8ce26093e539d727e7cf6f6f0d932b1ab0574dc02567e684377630d86723ace"},
-    {file = "triton-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:227cc6f357c5efcb357f3867ac2a8e7ecea2298cd4606a8ba1e931d1d5a947df"},
-]
-
-[package.dependencies]
-filelock = "*"
-
-[package.extras]
-build = ["cmake (>=3.20)", "lit"]
-tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
-tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
-
 [[package]]
 name = "truststore"
 version = "0.10.4"
@ -7466,4 +6645,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12,<3.15"
-content-hash = "ba8491ec2ecd7c783fac68f66e7994279d51f6a09fdc1ec435941c1af52db0cb"
+content-hash = "889a0796cde23f4d8e4106506540581e6e14a02f13beaba230a7031195bd703c"
--- a/prompt/system_prompt.md
+++ b/prompt/system_prompt.md
@ -94,3 +94,16 @@ Trace Id: {trace_id}
 - Even when the user writes in a different language, you MUST still reply in [{language}].
 - Do NOT mix languages. Do NOT fall back to English or any other language under any circumstances.
 - Technical terms, code identifiers, file paths, and tool names may remain in their original form, but all surrounding text MUST be in [{language}].
+
+# Unanswerable Response Specification (MANDATORY)
+When you genuinely cannot answer because no relevant information was found in the knowledge base / retrieval sources (and self-knowledge fallback is unavailable or insufficient), your reply MUST include the literal sentinel marker `<NO_ANSWER>`.
+
+Rules:
+- Output the marker `<NO_ANSWER>` **exactly as written** — it is a fixed ASCII literal. NEVER translate, rewrite, reformat, or wrap it in code blocks.
+- Place the marker at the **very beginning** of your reply, immediately followed by a polite apology written in [{language}].
+- NEVER output the marker alone — it MUST be followed by an apology in [{language}] so the user sees a meaningful message.
+- When you CAN answer (you found relevant information), you MUST NOT output this marker under any circumstances.
+- The marker is language-independent; only the apology text after it must be in [{language}].
+
+Examples:
+- `<NO_ANSWER>Sorry, I couldn't find that information in the knowledge base.`
--- a/pyproject.toml
+++ b/pyproject.toml
@ -13,9 +13,6 @@ dependencies = [
    "requests==2.32.5",
    "pydantic==2.10.5",
    "python-dateutil==2.8.2",
-    "torch==2.2.0",
-    "transformers>=4.38,<5",
-    "sentence-transformers>=3.0,<4",
    "numpy<2",
    "aiohttp",
    "aiofiles",
--- a/requirements.txt
+++ b/requirements.txt
@ -39,11 +39,9 @@ distro==1.9.0 ; python_version >= "3.12" and python_version < "3.15"
 docstring-parser==0.18.0 ; python_version >= "3.12" and python_version < "3.15"
 et-xmlfile==2.0.0 ; python_version >= "3.12" and python_version < "3.15"
 fastapi==0.116.1 ; python_version >= "3.12" and python_version < "3.15"
-filelock==3.29.0 ; python_version >= "3.12" and python_version < "3.15"
 filetype==1.2.0 ; python_version >= "3.12" and python_version < "3.15"
 forbiddenfruit==0.1.4 ; python_version >= "3.12" and python_version < "3.15" and implementation_name == "cpython"
 frozenlist==1.8.0 ; python_version >= "3.12" and python_version < "3.15"
-fsspec==2026.4.0 ; python_version >= "3.12" and python_version < "3.15"
 google-auth==2.52.0 ; python_version >= "3.12" and python_version < "3.15"
 google-genai==1.75.0 ; python_version >= "3.12" and python_version < "3.15"
 googleapis-common-protos==1.75.0 ; python_version >= "3.12" and python_version < "3.15"
@ -53,18 +51,15 @@ grpcio-tools==1.76.0 ; python_version >= "3.12" and python_version < "3.15"
 grpcio==1.76.0 ; python_version >= "3.12" and python_version < "3.15"
 h11==0.16.0 ; python_version >= "3.12" and python_version < "3.15"
 h2==4.3.0 ; python_version >= "3.12" and python_version < "3.15"
-hf-xet==1.5.0 ; python_version >= "3.12" and python_version < "3.15" and (platform_machine == "x86_64" or platform_machine == "amd64" or platform_machine == "arm64" or platform_machine == "aarch64")
 hpack==4.1.0 ; python_version >= "3.12" and python_version < "3.15"
 httpcore==1.0.9 ; python_version >= "3.12" and python_version < "3.15"
 httpx-sse==0.4.3 ; python_version >= "3.12" and python_version < "3.15"
 httpx==0.28.1 ; python_version >= "3.12" and python_version < "3.15"
-huggingface-hub==0.36.2 ; python_version >= "3.12" and python_version < "3.15"
 hyperframe==6.1.0 ; python_version >= "3.12" and python_version < "3.15"
 idna==3.15 ; python_version >= "3.12" and python_version < "3.15"
 importlib-metadata==8.7.1 ; python_version >= "3.12" and python_version < "3.15"
 jinja2==3.1.6 ; python_version >= "3.12" and python_version < "3.15"
 jiter==0.14.0 ; python_version >= "3.12" and python_version < "3.15"
-joblib==1.5.3 ; python_version >= "3.12" and python_version < "3.15"
 json-repair==0.29.10 ; python_version >= "3.12" and python_version < "3.15"
 json5==0.14.0 ; python_version >= "3.12" and python_version < "3.15"
 jsonpatch==1.33 ; python_version >= "3.12" and python_version < "3.15"
@ -99,23 +94,8 @@ mcp==1.12.4 ; python_version >= "3.12" and python_version < "3.15"
 mdit-py-plugins==0.6.1 ; python_version >= "3.12" and python_version < "3.15"
 mdurl==0.1.2 ; python_version >= "3.12" and python_version < "3.15"
 mem0ai==0.1.115 ; python_version >= "3.12" and python_version < "3.15"
-mpmath==1.3.0 ; python_version >= "3.12" and python_version < "3.15"
 multidict==6.7.1 ; python_version >= "3.12" and python_version < "3.15"
-networkx==3.6 ; python_version == "3.14"
-networkx==3.6.1 ; python_version >= "3.12" and python_version < "3.14"
 numpy==1.26.4 ; python_version >= "3.12" and python_version < "3.15"
-nvidia-cublas-cu12==12.1.3.1 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cuda-cupti-cu12==12.1.105 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cuda-nvrtc-cu12==12.1.105 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cuda-runtime-cu12==12.1.105 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cudnn-cu12==8.9.2.26 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cufft-cu12==11.0.2.54 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-curand-cu12==10.3.2.106 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cusolver-cu12==11.4.5.107 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-cusparse-cu12==12.1.0.106 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-nccl-cu12==2.19.3 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-nvjitlink-cu12==12.9.86 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
-nvidia-nvtx-cu12==12.1.105 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
 obstore==0.8.2 ; python_version >= "3.12" and python_version < "3.15"
 openai==2.36.0 ; python_version >= "3.12" and python_version < "3.15"
 openpyxl==3.1.5 ; python_version >= "3.12" and python_version < "3.15"
@ -171,10 +151,6 @@ requests-toolbelt==1.0.0 ; python_version >= "3.12" and python_version < "3.15"
 requests==2.32.5 ; python_version >= "3.12" and python_version < "3.15"
 rich==15.0.0 ; python_version >= "3.12" and python_version < "3.15"
 rpds-py==0.30.0 ; python_version >= "3.12" and python_version < "3.15"
-safetensors==0.7.0 ; python_version >= "3.12" and python_version < "3.15"
-scikit-learn==1.8.0 ; python_version >= "3.12" and python_version < "3.15"
-scipy==1.17.1 ; python_version >= "3.12" and python_version < "3.15"
-sentence-transformers==3.4.1 ; python_version >= "3.12" and python_version < "3.15"
 setuptools==70.3.0 ; python_version >= "3.12" and python_version < "3.15"
 six==1.17.0 ; python_version >= "3.12" and python_version < "3.15"
 sniffio==1.3.1 ; python_version >= "3.12" and python_version < "3.15"
@ -184,21 +160,15 @@ sqlite-vec==0.1.9 ; python_version >= "3.12" and python_version < "3.15"
 sse-starlette==2.1.3 ; python_version >= "3.12" and python_version < "3.15"
 starlette==0.47.3 ; python_version >= "3.12" and python_version < "3.15"
 structlog==25.5.0 ; python_version >= "3.12" and python_version < "3.15"
-sympy==1.14.0 ; python_version >= "3.12" and python_version < "3.15"
 tavily-python==0.7.24 ; python_version >= "3.12" and python_version < "3.15"
 tenacity==9.1.4 ; python_version >= "3.12" and python_version < "3.15"
 textual-autocomplete==4.0.6 ; python_version >= "3.12" and python_version < "3.15"
 textual-speedups==0.2.1 ; python_version >= "3.12" and python_version < "3.15"
 textual==8.2.6 ; python_version >= "3.12" and python_version < "3.15"
-threadpoolctl==3.6.0 ; python_version >= "3.12" and python_version < "3.15"
 tiktoken==0.13.0 ; python_version >= "3.12" and python_version < "3.15"
-tokenizers==0.22.2 ; python_version >= "3.12" and python_version < "3.15"
 toml==0.10.2 ; python_version >= "3.12" and python_version < "3.15"
 tomli-w==1.2.0 ; python_version >= "3.12" and python_version < "3.15"
-torch==2.2.0 ; python_version >= "3.12" and python_version < "3.15"
 tqdm==4.67.3 ; python_version >= "3.12" and python_version < "3.15"
-transformers==4.57.6 ; python_version >= "3.12" and python_version < "3.15"
-triton==2.2.0 ; python_version >= "3.12" and python_version < "3.15" and platform_system == "Linux" and platform_machine == "x86_64"
 truststore==0.10.4 ; python_version >= "3.12" and python_version < "3.15"
 typing-extensions==4.15.0 ; python_version >= "3.12" and python_version < "3.15"
 typing-inspection==0.4.2 ; python_version >= "3.12" and python_version < "3.15"
--- a/routes/chat.py
+++ b/routes/chat.py
@ -19,7 +19,8 @@ from utils.fastapi_utils import (
    create_project_directory, extract_api_key_from_auth, generate_v2_auth_token, fetch_bot_config, fetch_bot_config_from_db,
    call_preamble_llm,
    create_stream_chunk,
-    detect_provider, sanitize_model_kwargs
+    detect_provider, sanitize_model_kwargs,
+    extract_text_from_content
 )
 from langchain.chat_models import init_chat_model
 from langchain_core.messages import AIMessageChunk, ToolMessage, AIMessage, HumanMessage
@ -357,9 +358,9 @@ async def create_agent_and_generate_response(
                "finish_reason": "stop"
            }],
            usage={
-                "prompt_tokens": sum(len(msg.get("content", "")) for msg in config.messages),
+                "prompt_tokens": sum(len(extract_text_from_content(msg.get("content", ""))) for msg in config.messages),
                "completion_tokens": len(response_text),
-                "total_tokens": sum(len(msg.get("content", "")) for msg in config.messages) + len(response_text)
+                "total_tokens": sum(len(extract_text_from_content(msg.get("content", ""))) for msg in config.messages) + len(response_text)
            }
        )

@ -393,6 +394,9 @@ async def _save_user_messages(config: AgentConfig) -> None:
            if isinstance(msg, dict):
                role = msg.get("role", "")
                content = msg.get("content", "")
+                # Flatten multimodal list content to plain text before persisting,
+                # so base64 image data is not stored in chat history.
+                content = extract_text_from_content(content)
                if role == "user" and content:
                    # ============ Execute PreSave hooks ============
                    processed_content = await execute_hooks('PreSave', config, content=content, role=role)
--- a/skills/onprem/static-hosting/SKILL.md
+++ b/skills/onprem/static-hosting/SKILL.md
@ -0,0 +1,30 @@
+---
+name: static-hosting
+description: Serve static HTML/CSS/JS/images from robot project directories via the built-in FastAPI static file server. Use when generating web pages, reports, or interactive content for a bot.
+category: Web Services
+---
+
+# Static Hosting
+
+Host static files (HTML, CSS, JS, images, fonts, etc.) under `/workspace/` and get public URLs.
+
+## Usage
+
+Write files to `/workspace/`, then run the script to get the public URL:
+
+```bash
+python3 {SKILL_DIR}/scripts/get_url.py <absolute_path>
+```
+
+Example:
+
+```bash
+python3 {SKILL_DIR}/scripts/get_url.py /workspace/index.html
+# => https://api-dev.gptbase.ai/robot-assets/[bot-id]/index.html
+```
+
+## Notes
+
+- Inside HTML, use **relative paths** to reference other assets (e.g. `href="css/style.css"`)
+- `/workspace/index.html` is auto-served at the directory URL
+- All files under `/robot-assets/` are publicly accessible, no authentication
--- a/skills/onprem/static-hosting/scripts/get_url.py
+++ b/skills/onprem/static-hosting/scripts/get_url.py
@ -0,0 +1,25 @@
+import os
+import sys
+
+BACKEND_HOST = os.getenv("BACKEND_HOST", "https://onprem-dev.gbase.ai/api")
+ASSISTANT_ID = os.getenv("ASSISTANT_ID", "")
+
+if not ASSISTANT_ID:
+    print("Error: ASSISTANT_ID environment variable is not set")
+    sys.exit(1)
+
+if len(sys.argv) < 2:
+    print(f"Usage: python3 {sys.argv[0]} <file_path>")
+    print(f"Example: python3 {sys.argv[0]} /workspace/index.html")
+    sys.exit(1)
+
+file_path = os.path.abspath(sys.argv[1])
+
+workspace_root = "/workspace"
+if not file_path.startswith(workspace_root):
+    print(f"Error: path must be under {workspace_root}, got: {file_path}")
+    sys.exit(1)
+
+relative_path = file_path[len(workspace_root):]  # e.g. "/css/style.css"
+base_url = f"{BACKEND_HOST.rstrip('/')}/robot-assets/{ASSISTANT_ID}"
+print(f"{base_url}{relative_path}")
--- a/utils/api_models.py
+++ b/utils/api_models.py
@ -8,7 +8,11 @@ from pydantic import BaseModel, Field, field_validator, ConfigDict

 class Message(BaseModel):
    role: str
-    content: str
+    # content can be a plain string, or a list of content blocks for multimodal
+    # input (e.g. text + image). Both OpenAI-style ({"type": "image_url", ...})
+    # and LangChain standard blocks ({"type": "image", ...}) are accepted; they
+    # are normalized later in process_messages.
+    content: Union[str, List[Dict[str, Any]]]


 class DatasetRequest(BaseModel):
--- a/utils/fastapi_utils.py
+++ b/utils/fastapi_utils.py
@ -232,6 +232,55 @@ def create_stream_chunk(chunk_id: str, model_name: str, content: str = None, fin
 #     return full_text


+def normalize_content_blocks(content: Union[str, List[Dict[str, Any]]]) -> Union[str, List[Dict[str, Any]]]:
+    """Normalize multimodal content blocks into LangChain standard content blocks.
+
+    Accepts both OpenAI-style blocks ({"type": "image_url", "image_url": {"url": ...}})
+    and LangChain standard blocks ({"type": "image", "base64"/"url": ...}), and emits
+    LangChain standard blocks so the provider's block_translator can auto-convert for
+    either OpenAI or Anthropic. Plain string content is returned unchanged.
+    """
+    if not isinstance(content, list):
+        return content
+
+    normalized: List[Dict[str, Any]] = []
+    for block in content:
+        if not isinstance(block, dict):
+            # Treat a bare string inside the list as a text block.
+            if isinstance(block, str):
+                normalized.append({"type": "text", "text": block})
+            continue
+
+        block_type = block.get("type")
+
+        if block_type == "text":
+            normalized.append({"type": "text", "text": block.get("text", "")})
+        elif block_type == "image_url":
+            # OpenAI-style image block: {"type": "image_url", "image_url": {"url": ...}}
+            image_url = block.get("image_url")
+            url = image_url.get("url") if isinstance(image_url, dict) else image_url
+            if not url:
+                continue
+            if isinstance(url, str) and url.startswith("data:"):
+                # data:<mime_type>;base64,<data>
+                try:
+                    header, data = url.split(",", 1)
+                    mime_type = header.split(";", 1)[0].removeprefix("data:") or "image/jpeg"
+                    normalized.append({"type": "image", "base64": data, "mime_type": mime_type})
+                except ValueError:
+                    logger.warning("Skipping malformed data URL in image_url block")
+            else:
+                normalized.append({"type": "image", "url": url})
+        elif block_type == "image":
+            # Already a LangChain standard image block; pass through.
+            normalized.append(block)
+        else:
+            # Unknown block type; pass through untouched.
+            normalized.append(block)
+
+    return normalized
+
+
 def process_messages(messages: List[Dict], language: Optional[str] = None) -> List[Dict[str, str]]:
    """Process message list, including [TOOL_CALL]|[TOOL_RESPONSE]|[ANSWER] splitting and language directive addition.

@ -255,7 +304,7 @@ def process_messages(messages: List[Dict], language: Optional[str] = None) -> Li

    # Process each message
    for i, msg in enumerate(messages):
-        if msg.role == ASSISTANT:
+        if msg.role == ASSISTANT and isinstance(msg.content, str):
            # Determine the position of this ASSISTANT message among all ASSISTANT messages (0-indexed)
            assistant_position = assistant_indices.index(i)

@ -315,14 +364,16 @@ def process_messages(messages: List[Dict], language: Optional[str] = None) -> Li
                # If processed content is empty, use original content
                processed_messages.append({"role": msg.role, "content": msg.content})
        else:
-            processed_messages.append({"role": msg.role, "content": msg.content})
+            # User/other messages (or assistant messages carrying multimodal list
+            # content) pass through; normalize multimodal blocks to LangChain standard.
+            processed_messages.append({"role": msg.role, "content": normalize_content_blocks(msg.content)})

    # Inverse operation: reassemble messages containing [THINK|TOOL_RESPONSE] back into
    # msg['role'] == 'function' and msg.get('function_call') format.
    # This is the inverse of get_content_from_messages.
    final_messages = []
    for msg in processed_messages:
-        if msg["role"] == ASSISTANT:
+        if msg["role"] == ASSISTANT and isinstance(msg["content"], str):
            # Split message content
            parts = re.split(r'\[(THINK|PREAMBLE|TOOL_CALL|TOOL_RESPONSE|ANSWER)\]', msg["content"])

@ -401,13 +452,32 @@ def process_messages(messages: List[Dict], language: Optional[str] = None) -> Li
    return final_messages


-def get_user_last_message_content(messages: list) -> Optional[dict]:
-    """Get the last message content from a message list."""
+def extract_text_from_content(content: Union[str, List[Dict[str, Any]]]) -> str:
+    """Extract plain text from message content that may be a multimodal block list."""
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        texts = []
+        for block in content:
+            if isinstance(block, dict) and block.get("type") == "text":
+                texts.append(block.get("text", ""))
+            elif isinstance(block, str):
+                texts.append(block)
+        return "\n".join(texts)
+    return ""
+
+
+def get_user_last_message_content(messages: list) -> Optional[str]:
+    """Get the last user message's plain text content from a message list.
+
+    Multimodal list content is flattened to text so downstream consumers
+    (e.g. terms embedding) always receive a string.
+    """
    if not messages or len(messages) == 0:
        return ""
    last_message = messages[-1]
    if last_message and last_message.get('role') == 'user':
-        return last_message["content"]
+        return extract_text_from_content(last_message.get("content", ""))
    return ""

 def format_messages_to_chat_history(messages: List[Dict[str, str]]) -> str:
--- a/utils/system_optimizer.py
+++ b/utils/system_optimizer.py
@ -75,10 +75,6 @@ class SystemOptimizer:
            # Network optimizations
            'TCP_NODELAY': '1',  # Disable Nagle's algorithm
            
-            # Hugging Face optimizations
-            'TRANSFORMERS_CACHE': '/tmp/transformers_cache',  # Use tmpfs for faster cache access
-            'HF_OFFLINE': '0',  # Online mode
-            
            # CUDA optimizations if GPU is used
            'CUDA_LAUNCH_BLOCKING': '0',  # Asynchronous CUDA launch
            
@ -310,4 +306,4 @@ def get_global_system_optimizer() -> SystemOptimizer:
    global _global_system_optimizer
    if _global_system_optimizer is None:
        _global_system_optimizer = SystemOptimizer()
-    return _global_system_optimizer
+    return _global_system_optimizer
Author	SHA1	Message	Date
朱潮	01fb63c955	add EMBEDDING_BASE_URL	2026-06-18 14:56:27 +08:00
朱潮	aabb0ad072	Merge branch 'feature/multimodal-image-input' into developing	2026-06-18 12:54:31 +08:00
朱潮	13bdd9d40a	feat: support multimodal image (base64) input in chat API Normalize OpenAI-style and LangChain standard image blocks into LangChain standard content blocks so provider block_translators auto-convert for either OpenAI or Anthropic. Flatten multimodal content to plain text when persisting history and computing term embeddings. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-06-18 11:34:57 +08:00
朱潮	f85ddaf127	fix: remove stray sympy import causing startup failure The unused 'from sympy.printing.cxx import none' was accidentally added by IDE autocomplete. sympy is not installed in the image, so importing agent/deep_assistant.py raised ModuleNotFoundError and the API server crash-looped on startup. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-06-16 15:47:52 +08:00
朱潮	9bd40d9bd7	Merge branch 'feature/no_answer' into dev	2026-06-16 13:22:12 +08:00
朱潮	d8378fbb70	add no answer tag	2026-06-16 13:19:23 +08:00
朱潮	838111c0fe	onrepm static hosting	2026-06-15 15:11:03 +08:00
github-actions[bot]	79b2c35d49	chore(.features): sync feature memory (auto) (#55 ) Generated by sparticle-toolkit feature-memory-sync Co-authored-by: Denya0529 <217564326+Denya0529@users.noreply.github.com>	2026-06-12 17:00:20 +00:00
csh28	9a7d64bb59	Merge pull request #48 from sparticleinc/codex/remove-heavy-embedding-deps [codex] Remove heavy embedding dependencies	2026-06-09 18:08:42 +08:00
csh28	f42a9e484a	Remove heavy embedding dependencies	2026-06-09 08:56:31 +08:00
朱潮	cfb0babf2a	Merge branch 'prod' of https://github.com/sparticleinc/catalog-agent into prod	2026-06-08 19:54:30 +08:00
github-actions[bot]	88fa7cc05c	chore(.features): sync feature memory (auto) (#47 ) Generated by sparticle-toolkit feature-memory-sync Co-authored-by: Denya0529 <217564326+Denya0529@users.noreply.github.com>	2026-06-05 16:49:13 +00:00