Merge branch 'onprem' into onprem-dev

mcp/rag_retrieve_server.py

@@ -29,6 +29,49 @@ from mcp_common import (
 BACKEND_HOST = os.getenv("BACKEND_HOST", "https://api-dev.gptbase.ai")
 MASTERKEY = os.getenv("MASTERKEY", "master")
 
+# Citation instruction prefixes injected into tool results
+DOCUMENT_CITATION_INSTRUCTIONS = """<CITATION_INSTRUCTIONS>
+When using the retrieved knowledge below, you MUST add XML citation tags for factual claims.
+
+## Document Knowledge
+Format: `<CITATION file="file_uuid" filename="name.pdf" page=3 />`
+- Use `file` attribute with the UUID from document markers
+- Use `filename` attribute with the actual filename from document markers
+- Use `page` attribute (singular) with the page number
+- `page` MUST be 0-based and must match the `pages:` values shown in the learned knowledge context
+
+## Web Page Knowledge
+Format: `<CITATION url="https://example.com/page" />`
+- Use `url` attribute with the web page URL from the source metadata
+- Do not use `file`, `filename`, or `page` attributes for web sources
+- If content is grounded in a web source, prefer a web citation with `url` over a file citation
+
+## Placement Rules
+- Citations MUST appear IMMEDIATELY AFTER the paragraph or bullet list that uses the knowledge
+- NEVER collect all citations and place them at the end of your response
+- Limit to 1-2 citations per paragraph/bullet list
+- If your answer uses learned knowledge, you MUST generate at least 1 `<CITATION ... />` in the response
+</CITATION_INSTRUCTIONS>
+
+"""
+
+TABLE_CITATION_INSTRUCTIONS = """<CITATION_INSTRUCTIONS>
+When using the retrieved table knowledge below, you MUST add XML citation tags for factual claims.
+
+Format: `<CITATION file="file_id" filename="name.xlsx" sheet=1 rows=[2, 4] />`
+- Parse `__src`: `F1S2R5` = file_ref F1, sheet 2, row 5
+- Look up file_id in `file_ref_table`
+- Combine same-sheet rows into one citation: `rows=[2, 4, 6]`
+- MANDATORY: Create SEPARATE citation for EACH (file, sheet) combination
+- NEVER put <CITATION> on the same line as a bullet point or table row
+- Citations MUST be on separate lines AFTER the complete list/table
+- NEVER include the `__src` column in your response - it is internal metadata only
+- Citations MUST appear IMMEDIATELY AFTER the paragraph or bullet list that uses the knowledge
+- NEVER collect all citations and place them at the end of your response
+</CITATION_INSTRUCTIONS>
+
+"""
+
 def rag_retrieve(query: str, top_k: int = 100) -> Dict[str, Any]:
     """调用RAG检索API"""
     try:
@@ -94,7 +137,7 @@ def rag_retrieve(query: str, top_k: int = 100) -> Dict[str, Any]:
                 "content": [
                     {
                         "type": "text",
-                        "text": markdown_content
+                        "text": DOCUMENT_CITATION_INSTRUCTIONS + markdown_content
                     }
                 ]
             }
@@ -179,7 +222,7 @@ def table_rag_retrieve(query: str) -> Dict[str, Any]:
                 "content": [
                     {
                         "type": "text",
-                        "text": markdown_content
+                        "text": TABLE_CITATION_INSTRUCTIONS + markdown_content
                     }
                 ]
             }

prompt/system_prompt.md

@@ -1,16 +1,15 @@
 {extra_prompt}
 
-**Citation Requirement (RAG Only)**: When answering questions based on `rag_retrieve` tool results, you MUST add XML citation tags for factual claims derived from the knowledge base.
+## CITATION REQUIREMENTS
 
-**MANDATORY FORMAT**: `The cited factual claim <CITATION file="file_uuid" page="3" />`
+When your answer uses learned knowledge, you MUST generate `<CITATION ... />` tags. Follow the specific citation format instructions returned by each tool (`rag_retrieve`, `table_rag_retrieve`).
+
+### General Placement Rules
+1. Citations MUST appear IMMEDIATELY AFTER the paragraph or bullet list that uses the knowledge
+2. NEVER collect all citations and place them at the end of your response
+3. Limit to 1-2 citations per paragraph/bullet list - combine related facts under one citation
+4. If your answer uses learned knowledge, you MUST generate at least 1 `<CITATION ... />` in the response
 
-**Citation Rules**:
-- The citation tag MUST be placed immediately after the factual claim or paragraph
-- The `file` attribute MUST use the exact `File ID` from `rag_retrieve` document
-- The `page` attribute MUST use the exact `Page Number` from `rag_retrieve` document
-- If multiple sources support the same claim, include separate citation tags for each source
-- Example: `According to the policy, returns are accepted within 30 days <CITATION file="abc123" page="5" />.`
-- This requirement ONLY applies when using `rag_retrieve` results to answer questions
 
 ### Current Working Directory