From 88fa7cc05c89a0e660de02f09ad9b96b8718217a Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Fri, 5 Jun 2026 16:49:13 +0000 Subject: [PATCH 1/7] chore(.features): sync feature memory (auto) (#47) Generated by sparticle-toolkit feature-memory-sync Co-authored-by: Denya0529 <217564326+Denya0529@users.noreply.github.com> --- .features/skill/MEMORY.md | 6 ++++ .features/skill/changelog/2026-Q2.md | 51 ++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) diff --git a/.features/skill/MEMORY.md b/.features/skill/MEMORY.md index 915fac2..5a2c15b 100644 --- a/.features/skill/MEMORY.md +++ b/.features/skill/MEMORY.md @@ -1,6 +1,7 @@ # Skill 功能 > 负责范围：技能包管理服务 - 核心实现 +> 最后更新：2026-06-02 > 最后更新：2026-05-26 > 最后更新：2026-05-23 > 最后更新：2026-04-20 @@ -28,9 +29,12 @@ 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 +- [2026-06-02](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`） @@ -85,6 +89,8 @@ 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。 ## Skill 目录结构 diff --git a/.features/skill/changelog/2026-Q2.md b/.features/skill/changelog/2026-Q2.md index ca34c8e..86b46f2 100644 --- a/.features/skill/changelog/2026-Q2.md +++ b/.features/skill/changelog/2026-Q2.md @@ -4,6 +4,57 @@ --- +## 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 From f42a9e484a3cb475bf333dcf3a5535cbf9f89e14 Mon Sep 17 00:00:00 2001 From: csh28 Date: Tue, 9 Jun 2026 08:56:31 +0800 Subject: [PATCH 2/7] Remove heavy embedding dependencies --- poetry.lock | 763 +------------------------------------- pyproject.toml | 3 - requirements.txt | 29 -- utils/system_optimizer.py | 6 +- 4 files changed, 5 insertions(+), 796 deletions(-) diff --git a/poetry.lock b/poetry.lock index 7c6806d..aa53671 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.4.1 and should not be changed by hand. [[package]] name = "agent-client-protocol" @@ -1091,18 +1091,6 @@ 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 = "3.20.0" -description = "A platform independent file lock." -optional = false -python-versions = ">=3.10" -groups = ["main"] -files = [ - {file = "filelock-3.20.0-py3-none-any.whl", hash = "sha256:339b4732ffda5cd79b13f4e2711a31b0365ce445d95d243bb996273d072546a2"}, - {file = "filelock-3.20.0.tar.gz", hash = "sha256:711e943b4ec6be42e1d4e6690b48dc175c822967466bb31c0c293f34334c13f4"}, -] - [[package]] name = "filetype" version = "1.2.0" @@ -1267,46 +1255,6 @@ files = [ {file = "frozenlist-1.8.0.tar.gz", hash = "sha256:3ede829ed8d842f6cd48fc7081d7a41001a56f1f38603f9d49bf3020d59a31ad"}, ] -[[package]] -name = "fsspec" -version = "2025.9.0" -description = "File-system specification" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "fsspec-2025.9.0-py3-none-any.whl", hash = "sha256:530dc2a2af60a414a832059574df4a6e10cce927f6f4a78209390fe38955cfb7"}, - {file = "fsspec-2025.9.0.tar.gz", hash = "sha256:19fd429483d25d28b65ec68f9f4adc16c17ea2c7c7bf54ec61360d478fb19c19"}, -] - -[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", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"] -fuse = ["fusepy"] -gcs = ["gcsfs"] -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"] -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)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "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 = "2.48.0" @@ -1642,28 +1590,6 @@ files = [ hpack = ">=4.1,<5" hyperframe = ">=6.1,<7" -[[package]] -name = "hf-xet" -version = "1.1.10" -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-1.1.10-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:686083aca1a6669bc85c21c0563551cbcdaa5cf7876a91f3d074a030b577231d"}, - {file = "hf_xet-1.1.10-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:71081925383b66b24eedff3013f8e6bbd41215c3338be4b94ba75fd75b21513b"}, - {file = "hf_xet-1.1.10-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b6bceb6361c80c1cc42b5a7b4e3efd90e64630bcf11224dcac50ef30a47e435"}, - {file = "hf_xet-1.1.10-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:eae7c1fc8a664e54753ffc235e11427ca61f4b0477d757cc4eb9ae374b69f09c"}, - {file = "hf_xet-1.1.10-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:0a0005fd08f002180f7a12d4e13b22be277725bc23ed0529f8add5c7a6309c06"}, - {file = "hf_xet-1.1.10-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f900481cf6e362a6c549c61ff77468bd59d6dd082f3170a36acfef2eb6a6793f"}, - {file = "hf_xet-1.1.10-cp37-abi3-win_amd64.whl", hash = "sha256:5f54b19cc347c13235ae7ee98b330c26dd65ef1df47e5316ffb1e87713ca7045"}, - {file = "hf_xet-1.1.10.tar.gz", hash = "sha256:408aef343800a2102374a883f283ff29068055c111f003ff840733d3b715bb97"}, -] - -[package.extras] -tests = ["pytest"] - [[package]] name = "hpack" version = "4.1.0" @@ -1790,45 +1716,6 @@ files = [ {file = "httpx_sse-0.4.3.tar.gz", hash = "sha256:9b1ed0127459a66014aec3c56bebd93da3c1bc8bb6618c8082039a44889a755d"}, ] -[[package]] -name = "huggingface-hub" -version = "0.35.3" -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-0.35.3-py3-none-any.whl", hash = "sha256:0e3a01829c19d86d03793e4577816fe3bdfc1602ac62c7fb220d593d351224ba"}, - {file = "huggingface_hub-0.35.3.tar.gz", hash = "sha256:350932eaa5cc6a4747efae85126ee220e4ef1b54e29d31c3b45c5612ddf0b32a"}, -] - -[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", "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", "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", "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" @@ -2022,18 +1909,6 @@ files = [ {file = "jiter-0.11.1.tar.gz", hash = "sha256:849dcfc76481c0ea0099391235b7ca97d7279e0fa4c86005457ac7c88e8b76dc"}, ] -[[package]] -name = "joblib" -version = "1.5.2" -description = "Lightweight pipelining with Python functions" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "joblib-1.5.2-py3-none-any.whl", hash = "sha256:4e1f0bdbb987e6d843c70cf43714cb276623def372df3c22fe5266b2670bc241"}, - {file = "joblib-1.5.2.tar.gz", hash = "sha256:3faa5c39054b2f03ca547da9b2f52fde67c06240c31853f306aea97f13647b55"}, -] - [[package]] name = "json-repair" version = "0.29.10" @@ -2099,7 +1974,7 @@ files = [ [package.dependencies] attrs = ">=22.2.0" -jsonschema-specifications = ">=2023.03.6" +jsonschema-specifications = ">=2023.3.6" referencing = ">=0.28.4" rpds-py = ">=0.7.1" @@ -2810,24 +2685,6 @@ 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 = "6.7.0" @@ -2984,27 +2841,6 @@ files = [ {file = "multidict-6.7.0.tar.gz", hash = "sha256:c6e99d9a65ca282e578dfea819cfa9c0a62b2499d8677392e09feaf305e9e6f5"}, ] -[[package]] -name = "networkx" -version = "3.5" -description = "Python package for creating and manipulating graphs and networks" -optional = false -python-versions = ">=3.11" -groups = ["main"] -files = [ - {file = "networkx-3.5-py3-none-any.whl", hash = "sha256:0030d386a9a06dee3565298b4a734b68589749a544acbb6c412dc9e2489ec6ec"}, - {file = "networkx-3.5.tar.gz", hash = "sha256:d4c6f9cf81f52d69230866796b82afbccdec3db7ae4fbd1b65ea750feed50037"}, -] - -[package.extras] -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)", "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)"] -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" @@ -3051,172 +2887,6 @@ 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" @@ -5205,209 +4875,6 @@ files = [ [package.dependencies] pyasn1 = ">=0.1.3" -[[package]] -name = "safetensors" -version = "0.6.2" -description = "" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "safetensors-0.6.2-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:9c85ede8ec58f120bad982ec47746981e210492a6db876882aa021446af8ffba"}, - {file = "safetensors-0.6.2-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:d6675cf4b39c98dbd7d940598028f3742e0375a6b4d4277e76beb0c35f4b843b"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1d2d2b3ce1e2509c68932ca03ab8f20570920cd9754b05063d4368ee52833ecd"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:93de35a18f46b0f5a6a1f9e26d91b442094f2df02e9fd7acf224cfec4238821a"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:89a89b505f335640f9120fac65ddeb83e40f1fd081cb8ed88b505bdccec8d0a1"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fc4d0d0b937e04bdf2ae6f70cd3ad51328635fe0e6214aa1fc811f3b576b3bda"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8045db2c872db8f4cbe3faa0495932d89c38c899c603f21e9b6486951a5ecb8f"}, - {file = "safetensors-0.6.2-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:81e67e8bab9878bb568cffbc5f5e655adb38d2418351dc0859ccac158f753e19"}, - {file = "safetensors-0.6.2-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:b0e4d029ab0a0e0e4fdf142b194514695b1d7d3735503ba700cf36d0fc7136ce"}, - {file = "safetensors-0.6.2-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:fa48268185c52bfe8771e46325a1e21d317207bcabcb72e65c6e28e9ffeb29c7"}, - {file = "safetensors-0.6.2-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:d83c20c12c2d2f465997c51b7ecb00e407e5f94d7dec3ea0cc11d86f60d3fde5"}, - {file = "safetensors-0.6.2-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:d944cea65fad0ead848b6ec2c37cc0b197194bec228f8020054742190e9312ac"}, - {file = "safetensors-0.6.2-cp38-abi3-win32.whl", hash = "sha256:cab75ca7c064d3911411461151cb69380c9225798a20e712b102edda2542ddb1"}, - {file = "safetensors-0.6.2-cp38-abi3-win_amd64.whl", hash = "sha256:c7b214870df923cbc1593c3faee16bec59ea462758699bd3fee399d00aac072c"}, - {file = "safetensors-0.6.2.tar.gz", hash = "sha256:43ff2aa0e6fa2dc3ea5524ac7ad93a9839256b8703761e76e2d0b2a3fa4f15d9"}, -] - -[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 = ["safetensors[numpy]", "torch (>=1.10)"] - -[[package]] -name = "scikit-learn" -version = "1.7.2" -description = "A set of python modules for machine learning and data mining" -optional = false -python-versions = ">=3.10" -groups = ["main"] -files = [ - {file = "scikit_learn-1.7.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6b33579c10a3081d076ab403df4a4190da4f4432d443521674637677dc91e61f"}, - {file = "scikit_learn-1.7.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:36749fb62b3d961b1ce4fedf08fa57a1986cd409eff2d783bca5d4b9b5fce51c"}, - {file = "scikit_learn-1.7.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7a58814265dfc52b3295b1900cfb5701589d30a8bb026c7540f1e9d3499d5ec8"}, - {file = "scikit_learn-1.7.2-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4a847fea807e278f821a0406ca01e387f97653e284ecbd9750e3ee7c90347f18"}, - {file = "scikit_learn-1.7.2-cp310-cp310-win_amd64.whl", hash = "sha256:ca250e6836d10e6f402436d6463d6c0e4d8e0234cfb6a9a47835bd392b852ce5"}, - {file = "scikit_learn-1.7.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c7509693451651cd7361d30ce4e86a1347493554f172b1c72a39300fa2aea79e"}, - {file = "scikit_learn-1.7.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:0486c8f827c2e7b64837c731c8feff72c0bd2b998067a8a9cbc10643c31f0fe1"}, - {file = "scikit_learn-1.7.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:89877e19a80c7b11a2891a27c21c4894fb18e2c2e077815bcade10d34287b20d"}, - {file = "scikit_learn-1.7.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8da8bf89d4d79aaec192d2bda62f9b56ae4e5b4ef93b6a56b5de4977e375c1f1"}, - {file = "scikit_learn-1.7.2-cp311-cp311-win_amd64.whl", hash = "sha256:9b7ed8d58725030568523e937c43e56bc01cadb478fc43c042a9aca1dacb3ba1"}, - {file = "scikit_learn-1.7.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8d91a97fa2b706943822398ab943cde71858a50245e31bc71dba62aab1d60a96"}, - {file = "scikit_learn-1.7.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:acbc0f5fd2edd3432a22c69bed78e837c70cf896cd7993d71d51ba6708507476"}, - {file = "scikit_learn-1.7.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5bf3d930aee75a65478df91ac1225ff89cd28e9ac7bd1196853a9229b6adb0b"}, - {file = "scikit_learn-1.7.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b4d6e9deed1a47aca9fe2f267ab8e8fe82ee20b4526b2c0cd9e135cea10feb44"}, - {file = "scikit_learn-1.7.2-cp312-cp312-win_amd64.whl", hash = "sha256:6088aa475f0785e01bcf8529f55280a3d7d298679f50c0bb70a2364a82d0b290"}, - {file = "scikit_learn-1.7.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0b7dacaa05e5d76759fb071558a8b5130f4845166d88654a0f9bdf3eb57851b7"}, - {file = "scikit_learn-1.7.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:abebbd61ad9e1deed54cca45caea8ad5f79e1b93173dece40bb8e0c658dbe6fe"}, - {file = "scikit_learn-1.7.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:502c18e39849c0ea1a5d681af1dbcf15f6cce601aebb657aabbfe84133c1907f"}, - {file = "scikit_learn-1.7.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7a4c328a71785382fe3fe676a9ecf2c86189249beff90bf85e22bdb7efaf9ae0"}, - {file = "scikit_learn-1.7.2-cp313-cp313-win_amd64.whl", hash = "sha256:63a9afd6f7b229aad94618c01c252ce9e6fa97918c5ca19c9a17a087d819440c"}, - {file = "scikit_learn-1.7.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:9acb6c5e867447b4e1390930e3944a005e2cb115922e693c08a323421a6966e8"}, - {file = "scikit_learn-1.7.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:2a41e2a0ef45063e654152ec9d8bcfc39f7afce35b08902bfe290c2498a67a6a"}, - {file = "scikit_learn-1.7.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98335fb98509b73385b3ab2bd0639b1f610541d3988ee675c670371d6a87aa7c"}, - {file = "scikit_learn-1.7.2-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:191e5550980d45449126e23ed1d5e9e24b2c68329ee1f691a3987476e115e09c"}, - {file = "scikit_learn-1.7.2-cp313-cp313t-win_amd64.whl", hash = "sha256:57dc4deb1d3762c75d685507fbd0bc17160144b2f2ba4ccea5dc285ab0d0e973"}, - {file = "scikit_learn-1.7.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fa8f63940e29c82d1e67a45d5297bdebbcb585f5a5a50c4914cc2e852ab77f33"}, - {file = "scikit_learn-1.7.2-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:f95dc55b7902b91331fa4e5845dd5bde0580c9cd9612b1b2791b7e80c3d32615"}, - {file = "scikit_learn-1.7.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9656e4a53e54578ad10a434dc1f993330568cfee176dff07112b8785fb413106"}, - {file = "scikit_learn-1.7.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96dc05a854add0e50d3f47a1ef21a10a595016da5b007c7d9cd9d0bffd1fcc61"}, - {file = "scikit_learn-1.7.2-cp314-cp314-win_amd64.whl", hash = "sha256:bb24510ed3f9f61476181e4db51ce801e2ba37541def12dc9333b946fc7a9cf8"}, - {file = "scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda"}, -] - -[package.dependencies] -joblib = ">=1.2.0" -numpy = ">=1.22.0" -scipy = ">=1.8.0" -threadpoolctl = ">=3.1.0" - -[package.extras] -benchmark = ["matplotlib (>=3.5.0)", "memory_profiler (>=0.57.0)", "pandas (>=1.4.0)"] -build = ["cython (>=3.0.10)", "meson-python (>=0.17.1)", "numpy (>=1.22.0)", "scipy (>=1.8.0)"] -docs = ["Pillow (>=8.4.0)", "matplotlib (>=3.5.0)", "memory_profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.4.0)", "plotly (>=5.14.0)", "polars (>=0.20.30)", "pooch (>=1.6.0)", "pydata-sphinx-theme (>=0.15.3)", "scikit-image (>=0.19.0)", "seaborn (>=0.9.0)", "sphinx (>=7.3.7)", "sphinx-copybutton (>=0.5.2)", "sphinx-design (>=0.5.0)", "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 (>=3.5.0)", "pandas (>=1.4.0)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.19.0)", "seaborn (>=0.9.0)"] -install = ["joblib (>=1.2.0)", "numpy (>=1.22.0)", "scipy (>=1.8.0)", "threadpoolctl (>=3.1.0)"] -maintenance = ["conda-lock (==3.0.1)"] -tests = ["matplotlib (>=3.5.0)", "mypy (>=1.15)", "numpydoc (>=1.2.0)", "pandas (>=1.4.0)", "polars (>=0.20.30)", "pooch (>=1.6.0)", "pyamg (>=4.2.1)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.11.7)", "scikit-image (>=0.19.0)"] - -[[package]] -name = "scipy" -version = "1.16.2" -description = "Fundamental algorithms for scientific computing in Python" -optional = false -python-versions = ">=3.11" -groups = ["main"] -files = [ - {file = "scipy-1.16.2-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:6ab88ea43a57da1af33292ebd04b417e8e2eaf9d5aa05700be8d6e1b6501cd92"}, - {file = "scipy-1.16.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c95e96c7305c96ede73a7389f46ccd6c659c4da5ef1b2789466baeaed3622b6e"}, - {file = "scipy-1.16.2-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:87eb178db04ece7c698220d523c170125dbffebb7af0345e66c3554f6f60c173"}, - {file = "scipy-1.16.2-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:4e409eac067dcee96a57fbcf424c13f428037827ec7ee3cb671ff525ca4fc34d"}, - {file = "scipy-1.16.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e574be127bb760f0dad24ff6e217c80213d153058372362ccb9555a10fc5e8d2"}, - {file = "scipy-1.16.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f5db5ba6188d698ba7abab982ad6973265b74bb40a1efe1821b58c87f73892b9"}, - {file = "scipy-1.16.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:ec6e74c4e884104ae006d34110677bfe0098203a3fec2f3faf349f4cb05165e3"}, - {file = "scipy-1.16.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:912f46667d2d3834bc3d57361f854226475f695eb08c08a904aadb1c936b6a88"}, - {file = "scipy-1.16.2-cp311-cp311-win_amd64.whl", hash = "sha256:91e9e8a37befa5a69e9cacbe0bcb79ae5afb4a0b130fd6db6ee6cc0d491695fa"}, - {file = "scipy-1.16.2-cp311-cp311-win_arm64.whl", hash = "sha256:f3bf75a6dcecab62afde4d1f973f1692be013110cad5338007927db8da73249c"}, - {file = "scipy-1.16.2-cp312-cp312-macosx_10_14_x86_64.whl", hash = "sha256:89d6c100fa5c48472047632e06f0876b3c4931aac1f4291afc81a3644316bb0d"}, - {file = "scipy-1.16.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:ca748936cd579d3f01928b30a17dc474550b01272d8046e3e1ee593f23620371"}, - {file = "scipy-1.16.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:fac4f8ce2ddb40e2e3d0f7ec36d2a1e7f92559a2471e59aec37bd8d9de01fec0"}, - {file = "scipy-1.16.2-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:033570f1dcefd79547a88e18bccacff025c8c647a330381064f561d43b821232"}, - {file = "scipy-1.16.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ea3421209bf00c8a5ef2227de496601087d8f638a2363ee09af059bd70976dc1"}, - {file = "scipy-1.16.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f66bd07ba6f84cd4a380b41d1bf3c59ea488b590a2ff96744845163309ee8e2f"}, - {file = "scipy-1.16.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:5e9feab931bd2aea4a23388c962df6468af3d808ddf2d40f94a81c5dc38f32ef"}, - {file = "scipy-1.16.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:03dfc75e52f72cf23ec2ced468645321407faad8f0fe7b1f5b49264adbc29cb1"}, - {file = "scipy-1.16.2-cp312-cp312-win_amd64.whl", hash = "sha256:0ce54e07bbb394b417457409a64fd015be623f36e330ac49306433ffe04bc97e"}, - {file = "scipy-1.16.2-cp312-cp312-win_arm64.whl", hash = "sha256:2a8ffaa4ac0df81a0b94577b18ee079f13fecdb924df3328fc44a7dc5ac46851"}, - {file = "scipy-1.16.2-cp313-cp313-macosx_10_14_x86_64.whl", hash = "sha256:84f7bf944b43e20b8a894f5fe593976926744f6c185bacfcbdfbb62736b5cc70"}, - {file = "scipy-1.16.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:5c39026d12edc826a1ef2ad35ad1e6d7f087f934bb868fc43fa3049c8b8508f9"}, - {file = "scipy-1.16.2-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:e52729ffd45b68777c5319560014d6fd251294200625d9d70fd8626516fc49f5"}, - {file = "scipy-1.16.2-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:024dd4a118cccec09ca3209b7e8e614931a6ffb804b2a601839499cb88bdf925"}, - {file = "scipy-1.16.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7a5dc7ee9c33019973a470556081b0fd3c9f4c44019191039f9769183141a4d9"}, - {file = "scipy-1.16.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c2275ff105e508942f99d4e3bc56b6ef5e4b3c0af970386ca56b777608ce95b7"}, - {file = "scipy-1.16.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:af80196eaa84f033e48444d2e0786ec47d328ba00c71e4299b602235ffef9acb"}, - {file = "scipy-1.16.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9fb1eb735fe3d6ed1f89918224e3385fbf6f9e23757cacc35f9c78d3b712dd6e"}, - {file = "scipy-1.16.2-cp313-cp313-win_amd64.whl", hash = "sha256:fda714cf45ba43c9d3bae8f2585c777f64e3f89a2e073b668b32ede412d8f52c"}, - {file = "scipy-1.16.2-cp313-cp313-win_arm64.whl", hash = "sha256:2f5350da923ccfd0b00e07c3e5cfb316c1c0d6c1d864c07a72d092e9f20db104"}, - {file = "scipy-1.16.2-cp313-cp313t-macosx_10_14_x86_64.whl", hash = "sha256:53d8d2ee29b925344c13bda64ab51785f016b1b9617849dac10897f0701b20c1"}, - {file = "scipy-1.16.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:9e05e33657efb4c6a9d23bd8300101536abd99c85cca82da0bffff8d8764d08a"}, - {file = "scipy-1.16.2-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:7fe65b36036357003b3ef9d37547abeefaa353b237e989c21027b8ed62b12d4f"}, - {file = "scipy-1.16.2-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:6406d2ac6d40b861cccf57f49592f9779071655e9f75cd4f977fa0bdd09cb2e4"}, - {file = "scipy-1.16.2-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ff4dc42bd321991fbf611c23fc35912d690f731c9914bf3af8f417e64aca0f21"}, - {file = "scipy-1.16.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:654324826654d4d9133e10675325708fb954bc84dae6e9ad0a52e75c6b1a01d7"}, - {file = "scipy-1.16.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:63870a84cd15c44e65220eaed2dac0e8f8b26bbb991456a033c1d9abfe8a94f8"}, - {file = "scipy-1.16.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:fa01f0f6a3050fa6a9771a95d5faccc8e2f5a92b4a2e5440a0fa7264a2398472"}, - {file = "scipy-1.16.2-cp313-cp313t-win_amd64.whl", hash = "sha256:116296e89fba96f76353a8579820c2512f6e55835d3fad7780fece04367de351"}, - {file = "scipy-1.16.2-cp313-cp313t-win_arm64.whl", hash = "sha256:98e22834650be81d42982360382b43b17f7ba95e0e6993e2a4f5b9ad9283a94d"}, - {file = "scipy-1.16.2-cp314-cp314-macosx_10_14_x86_64.whl", hash = "sha256:567e77755019bb7461513c87f02bb73fb65b11f049aaaa8ca17cfaa5a5c45d77"}, - {file = "scipy-1.16.2-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:17d9bb346194e8967296621208fcdfd39b55498ef7d2f376884d5ac47cec1a70"}, - {file = "scipy-1.16.2-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:0a17541827a9b78b777d33b623a6dcfe2ef4a25806204d08ead0768f4e529a88"}, - {file = "scipy-1.16.2-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:d7d4c6ba016ffc0f9568d012f5f1eb77ddd99412aea121e6fa8b4c3b7cbad91f"}, - {file = "scipy-1.16.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9702c4c023227785c779cba2e1d6f7635dbb5b2e0936cdd3a4ecb98d78fd41eb"}, - {file = "scipy-1.16.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d1cdf0ac28948d225decdefcc45ad7dd91716c29ab56ef32f8e0d50657dffcc7"}, - {file = "scipy-1.16.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:70327d6aa572a17c2941cdfb20673f82e536e91850a2e4cb0c5b858b690e1548"}, - {file = "scipy-1.16.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5221c0b2a4b58aa7c4ed0387d360fd90ee9086d383bb34d9f2789fafddc8a936"}, - {file = "scipy-1.16.2-cp314-cp314-win_amd64.whl", hash = "sha256:f5a85d7b2b708025af08f060a496dd261055b617d776fc05a1a1cc69e09fe9ff"}, - {file = "scipy-1.16.2-cp314-cp314-win_arm64.whl", hash = "sha256:2cc73a33305b4b24556957d5857d6253ce1e2dcd67fa0ff46d87d1670b3e1e1d"}, - {file = "scipy-1.16.2-cp314-cp314t-macosx_10_14_x86_64.whl", hash = "sha256:9ea2a3fed83065d77367775d689401a703d0f697420719ee10c0780bcab594d8"}, - {file = "scipy-1.16.2-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:7280d926f11ca945c3ef92ba960fa924e1465f8d07ce3a9923080363390624c4"}, - {file = "scipy-1.16.2-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:8afae1756f6a1fe04636407ef7dbece33d826a5d462b74f3d0eb82deabefd831"}, - {file = "scipy-1.16.2-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:5c66511f29aa8d233388e7416a3f20d5cae7a2744d5cee2ecd38c081f4e861b3"}, - {file = "scipy-1.16.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:efe6305aeaa0e96b0ccca5ff647a43737d9a092064a3894e46c414db84bc54ac"}, - {file = "scipy-1.16.2-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7f3a337d9ae06a1e8d655ee9d8ecb835ea5ddcdcbd8d23012afa055ab014f374"}, - {file = "scipy-1.16.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:bab3605795d269067d8ce78a910220262711b753de8913d3deeaedb5dded3bb6"}, - {file = "scipy-1.16.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:b0348d8ddb55be2a844c518cd8cc8deeeb8aeba707cf834db5758fc89b476a2c"}, - {file = "scipy-1.16.2-cp314-cp314t-win_amd64.whl", hash = "sha256:26284797e38b8a75e14ea6631d29bda11e76ceaa6ddb6fdebbfe4c4d90faf2f9"}, - {file = "scipy-1.16.2-cp314-cp314t-win_arm64.whl", hash = "sha256:d2a4472c231328d4de38d5f1f68fdd6d28a615138f842580a8a321b5845cf779"}, - {file = "scipy-1.16.2.tar.gz", hash = "sha256:af029b153d243a80afb6eabe40b0a07f8e35c9adc269c019f364ad747f826a6b"}, -] - -[package.dependencies] -numpy = ">=1.25.2,<2.6" - -[package.extras] -dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy (==1.10.0)", "pycodestyle", "pydevtool", "rich-click", "ruff (>=0.0.292)", "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)"] -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 = "5.1.1" -description = "Embeddings, Retrieval, and Reranking" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "sentence_transformers-5.1.1-py3-none-any.whl", hash = "sha256:5ed544629eafe89ca668a8910ebff96cf0a9c5254ec14b05c66c086226c892fd"}, - {file = "sentence_transformers-5.1.1.tar.gz", hash = "sha256:8af3f844b2ecf9a6c2dfeafc2c02938a87f61202b54329d70dfd7dfd7d17a84e"}, -] - -[package.dependencies] -huggingface-hub = ">=0.20.0" -Pillow = "*" -scikit-learn = "*" -scipy = "*" -torch = ">=1.11.0" -tqdm = "*" -transformers = ">=4.41.0,<5.0.0" -typing_extensions = ">=4.5.0" - -[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 = "80.9.0" @@ -5623,24 +5090,6 @@ 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 = "0.7.22" @@ -5824,18 +5273,6 @@ 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 = "0.12.0" @@ -5910,39 +5347,6 @@ requests = ">=2.26.0" [package.extras] blobfile = ["blobfile (>=2)"] -[[package]] -name = "tokenizers" -version = "0.22.1" -description = "" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "tokenizers-0.22.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:59fdb013df17455e5f950b4b834a7b3ee2e0271e6378ccb33aa74d178b513c73"}, - {file = "tokenizers-0.22.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:8d4e484f7b0827021ac5f9f71d4794aaef62b979ab7608593da22b1d2e3c4edc"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19d2962dd28bc67c1f205ab180578a78eef89ac60ca7ef7cbe9635a46a56422a"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38201f15cdb1f8a6843e6563e6e79f4abd053394992b9bbdf5213ea3469b4ae7"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1cbe5454c9a15df1b3443c726063d930c16f047a3cc724b9e6e1a91140e5a21"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7d094ae6312d69cc2a872b54b91b309f4f6fbce871ef28eb27b52a98e4d0214"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afd7594a56656ace95cdd6df4cca2e4059d294c5cfb1679c57824b605556cb2f"}, - {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2ef6063d7a84994129732b47e7915e8710f27f99f3a3260b8a38fc7ccd083f4"}, - {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ba0a64f450b9ef412c98f6bcd2a50c6df6e2443b560024a09fa6a03189726879"}, - {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:331d6d149fa9c7d632cde4490fb8bbb12337fa3a0232e77892be656464f4b446"}, - {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:607989f2ea68a46cb1dfbaf3e3aabdf3f21d8748312dbeb6263d1b3b66c5010a"}, - {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a0f307d490295717726598ef6fa4f24af9d484809223bbc253b201c740a06390"}, - {file = "tokenizers-0.22.1-cp39-abi3-win32.whl", hash = "sha256:b5120eed1442765cd90b903bb6cfef781fd8fe64e34ccaecbae4c619b7b12a82"}, - {file = "tokenizers-0.22.1-cp39-abi3-win_amd64.whl", hash = "sha256:65fd6e3fb11ca1e78a6a93602490f134d1fdeb13bcef99389d5102ea318ed138"}, - {file = "tokenizers-0.22.1.tar.gz", hash = "sha256:61de6522785310a309b3407bac22d99c4db5dba349935e99e4d15ea2226af2d9"}, -] - -[package.dependencies] -huggingface-hub = ">=0.16.4,<2.0" - -[package.extras] -dev = ["tokenizers[testing]"] -docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"] -testing = ["black (==22.3)", "datasets", "numpy", "pytest", "pytest-asyncio", "requests", "ruff"] - [[package]] name = "toml" version = "0.10.2" @@ -5967,65 +5371,6 @@ 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 = "4.67.1" @@ -6048,106 +5393,6 @@ notebook = ["ipywidgets (>=6)"] slack = ["slack-sdk"] telegram = ["requests"] -[[package]] -name = "transformers" -version = "4.57.1" -description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" -optional = false -python-versions = ">=3.9.0" -groups = ["main"] -files = [ - {file = "transformers-4.57.1-py3-none-any.whl", hash = "sha256:b10d05da8fa67dc41644dbbf9bc45a44cb86ae33da6f9295f5fbf5b7890bd267"}, - {file = "transformers-4.57.1.tar.gz", hash = "sha256:f06c837959196c75039809636cd964b959f6604b75b8eeec6fdfc0440b89cc55"}, -] - -[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" @@ -7129,9 +6374,9 @@ files = [ ] [package.extras] -cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and python_version < \"3.14\"", "cffi (>=2.0.0b) ; platform_python_implementation != \"PyPy\" and python_version >= \"3.14\""] +cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and python_version < \"3.14\"", "cffi (>=2.0.0b0) ; platform_python_implementation != \"PyPy\" and python_version >= \"3.14\""] [metadata] lock-version = "2.1" python-versions = ">=3.12,<3.15" -content-hash = "f5b01d5a1e60672741f2c5e8cc6e2ec55534963a9a3791fd1cdf67d3c2fbd70b" +content-hash = "af874fe9bf96a0a2468027b645438e4f4d955e965d4945083024fb33d79b5d7e" diff --git a/pyproject.toml b/pyproject.toml index d5163fd..594a6af 100644 --- 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", - "sentence-transformers", "numpy<2", "aiohttp", "aiofiles", diff --git a/requirements.txt b/requirements.txt index 4237427..a07f0b5 100644 --- a/requirements.txt +++ b/requirements.txt @@ -38,11 +38,9 @@ distro==1.9.0 ; python_version >= "3.12" and python_version < "3.15" docstring-parser==0.17.0 ; 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==3.20.0 ; 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==2025.9.0 ; python_version >= "3.12" and python_version < "3.15" google-auth==2.48.0 ; python_version >= "3.12" and python_version < "3.15" google-genai==1.65.0 ; python_version >= "3.12" and python_version < "3.15" googleapis-common-protos==1.74.0 ; python_version >= "3.12" and python_version < "3.15" @@ -52,19 +50,16 @@ grpcio-tools==1.78.0 ; python_version >= "3.12" and python_version < "3.15" grpcio==1.78.0 ; 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==1.1.10 ; 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" httptools==0.7.1 ; python_version >= "3.12" and python_version < "3.15" and platform_system != "Windows" 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==0.35.3 ; python_version >= "3.12" and python_version < "3.15" hyperframe==6.1.0 ; python_version >= "3.12" and python_version < "3.15" idna==3.11 ; 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==0.11.1 ; python_version >= "3.12" and python_version < "3.15" -joblib==1.5.2 ; python_version >= "3.12" and python_version < "3.15" json-repair==0.29.10 ; python_version >= "3.12" and python_version < "3.15" json5==0.13.0 ; python_version >= "3.12" and python_version < "3.15" jsonpatch==1.33 ; python_version >= "3.12" and python_version < "3.15" @@ -98,22 +93,8 @@ mcp==1.12.4 ; python_version >= "3.12" and python_version < "3.15" mdit-py-plugins==0.5.0 ; 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==6.7.0 ; python_version >= "3.12" and python_version < "3.15" -networkx==3.5 ; python_version >= "3.12" and python_version < "3.15" 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==2.31.0 ; python_version >= "3.12" and python_version < "3.15" openpyxl==3.1.5 ; python_version >= "3.12" and python_version < "3.15" @@ -168,10 +149,6 @@ requests==2.32.5 ; python_version >= "3.12" and python_version < "3.15" rich==14.2.0 ; python_version >= "3.12" and python_version < "3.15" rpds-py==0.27.1 ; python_version >= "3.12" and python_version < "3.15" rsa==4.9.1 ; python_version >= "3.12" and python_version < "3.15" -safetensors==0.6.2 ; python_version >= "3.12" and python_version < "3.15" -scikit-learn==1.7.2 ; python_version >= "3.12" and python_version < "3.15" -scipy==1.16.2 ; python_version >= "3.12" and python_version < "3.15" -sentence-transformers==5.1.1 ; python_version >= "3.12" and python_version < "3.15" setuptools==80.9.0 ; 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" @@ -181,21 +158,15 @@ sqlite-vec==0.1.6 ; python_version >= "3.12" and python_version < "3.15" sse-starlette==3.0.2 ; 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==0.7.22 ; python_version >= "3.12" and python_version < "3.15" tenacity==9.1.2 ; 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==8.0.0 ; python_version >= "3.12" and python_version < "3.15" -threadpoolctl==3.6.0 ; python_version >= "3.12" and python_version < "3.15" tiktoken==0.12.0 ; python_version >= "3.12" and python_version < "3.15" -tokenizers==0.22.1 ; 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==4.67.1 ; python_version >= "3.12" and python_version < "3.15" -transformers==4.57.1 ; 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" diff --git a/utils/system_optimizer.py b/utils/system_optimizer.py index 1f2b508..d4765b5 100644 --- 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 \ No newline at end of file + return _global_system_optimizer From 79b2c35d49e9818f017cbf74ea845e35d0bf06ab Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Fri, 12 Jun 2026 17:00:20 +0000 Subject: [PATCH 3/7] chore(.features): sync feature memory (auto) (#55) Generated by sparticle-toolkit feature-memory-sync Co-authored-by: Denya0529 <217564326+Denya0529@users.noreply.github.com> --- .features/skill/MEMORY.md | 5 ++ .features/skill/changelog/2026-Q2.md | 86 ++++++++++++++++++++++++++++ 2 files changed, 91 insertions(+) diff --git a/.features/skill/MEMORY.md b/.features/skill/MEMORY.md index 5a2c15b..cfc6fb6 100644 --- a/.features/skill/MEMORY.md +++ b/.features/skill/MEMORY.md @@ -1,6 +1,7 @@ # 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 > 最后更新：2026-05-23 @@ -33,6 +34,9 @@ MCP UI 类 skill 已按 MCP Apps 模式改造：工具返回数据，静态 HTML ## 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`） @@ -91,6 +95,7 @@ MCP UI 类 skill 已按 MCP Apps 模式改造：工具返回数据，静态 HTML - ⚠️ **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 diff --git a/.features/skill/changelog/2026-Q2.md b/.features/skill/changelog/2026-Q2.md index 86b46f2..c93f2fd 100644 --- a/.features/skill/changelog/2026-Q2.md +++ b/.features/skill/changelog/2026-Q2.md @@ -4,6 +4,92 @@ --- +## 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 From 838111c0fe5243ca85e829c25e3e70615c308d68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9C=B1=E6=BD=AE?= Date: Mon, 15 Jun 2026 15:11:03 +0800 Subject: [PATCH 4/7] onrepm static hosting --- skills/onprem/static-hosting/SKILL.md | 30 +++++++++++++++++++ .../onprem/static-hosting/scripts/get_url.py | 25 ++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 skills/onprem/static-hosting/SKILL.md create mode 100644 skills/onprem/static-hosting/scripts/get_url.py diff --git a/skills/onprem/static-hosting/SKILL.md b/skills/onprem/static-hosting/SKILL.md new file mode 100644 index 0000000..4058cf1 --- /dev/null +++ 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 +``` + +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 diff --git a/skills/onprem/static-hosting/scripts/get_url.py b/skills/onprem/static-hosting/scripts/get_url.py new file mode 100644 index 0000000..9def77b --- /dev/null +++ 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]} ") + 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}") From d8378fbb70568c1b57e709c6287d50571adac808 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9C=B1=E6=BD=AE?= Date: Tue, 16 Jun 2026 13:19:23 +0800 Subject: [PATCH 5/7] add no answer tag --- agent/mem0_manager.py | 31 +++++++++++++++++++++++++++++++ prompt/system_prompt.md | 13 +++++++++++++ 2 files changed, 44 insertions(+) diff --git a/agent/mem0_manager.py b/agent/mem0_manager.py index ed03b52..f939e86 100644 --- 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 diff --git a/prompt/system_prompt.md b/prompt/system_prompt.md index aff46de..39a2177 100644 --- 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 ``. + +Rules: +- Output the marker `` **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: +- `Sorry, I couldn't find that information in the knowledge base.` From f85ddaf1275930ae64ee7fc560556527fef06640 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9C=B1=E6=BD=AE?= Date: Tue, 16 Jun 2026 15:47:52 +0800 Subject: [PATCH 6/7] 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 --- agent/deep_assistant.py | 1 - 1 file changed, 1 deletion(-) diff --git a/agent/deep_assistant.py b/agent/deep_assistant.py index b6983eb..cf0168c 100644 --- 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 From 13bdd9d40a485b457db40aa2c98a6cb96366b4cd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9C=B1=E6=BD=AE?= Date: Thu, 18 Jun 2026 11:34:57 +0800 Subject: [PATCH 7/7] 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 --- agent/checkpoint_utils.py | 4 +- routes/chat.py | 10 +++-- utils/api_models.py | 8 +++- utils/fastapi_utils.py | 82 ++++++++++++++++++++++++++++++++++++--- 4 files changed, 92 insertions(+), 12 deletions(-) diff --git a/agent/checkpoint_utils.py b/agent/checkpoint_utils.py index 704b040..b23b268 100644 --- 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") diff --git a/routes/chat.py b/routes/chat.py index 0f03759..f06981b 100644 --- a/routes/chat.py +++ b/routes/chat.py @@ -18,7 +18,8 @@ from utils.fastapi_utils import ( process_messages, create_project_directory, extract_api_key_from_auth, generate_v2_auth_token, fetch_bot_config, call_preamble_llm, - create_stream_chunk + create_stream_chunk, + extract_text_from_content ) from langchain_core.messages import AIMessageChunk, ToolMessage, AIMessage, HumanMessage from utils.settings import MAX_OUTPUT_TOKENS @@ -355,9 +356,9 @@ 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) } ) @@ -391,6 +392,9 @@ 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) diff --git a/utils/api_models.py b/utils/api_models.py index 7ff4bce..4061bad 100644 --- a/utils/api_models.py +++ b/utils/api_models.py @@ -3,12 +3,16 @@ API data models and response schemas. """ -from typing import Dict, List, Optional, Any, AsyncGenerator +from typing import Dict, List, Optional, Any, AsyncGenerator, Union 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): diff --git a/utils/fastapi_utils.py b/utils/fastapi_utils.py index 6ab6762..cd5955f 100644 --- 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:;base64, + 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: