stwhite
/
ira
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improve reference formatting to ensure URLs are included

This commit is contained in:
Steve White 2025-02-28 17:02:22 -06:00
parent d53198d5ab
commit 3b75436423
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
report/report_synthesis.py
View File

@ -365,6 +365,7 @@ class ReportSynthesizer:
context += f"Document {i+1}:\n" context += f"Document {i+1}:\n"
context += f"Title: {title}\n" context += f"Title: {title}\n"
context += f"URL: {url}\n" context += f"URL: {url}\n"
context += f"Source URL: {url}\n" # Duplicate for emphasis
context += f"Extracted information:\n{chunk.get('extracted_info', '')}\n\n" context += f"Extracted information:\n{chunk.get('extracted_info', '')}\n\n"
# Get template modifier based on detail level and query type # Get template modifier based on detail level and query type
@ -377,11 +378,13 @@ class ReportSynthesizer:
[1] Title of the Article/Page. URL [1] Title of the Article/Page. URL
DO NOT use generic placeholders like "Document 1" for references. IMPORTANT:
Always use the actual title and URL from the source documents. 1. DO NOT use generic placeholders like "Document 1" for references
2. ALWAYS include the actual URL from the source documents
Always ensure the References section is complete and properly formatted at the end of the report. 3. Each reference MUST include both the title and the URL
Ensure all references are properly closed with brackets and there are no incomplete references. 4. Make sure all references are complete and properly formatted
5. Number the references sequentially starting from 1
6. Include the URL for EACH reference - this is critical.
""" """
# Special handling for Gemini models # Special handling for Gemini models
@ -432,13 +435,15 @@ class ReportSynthesizer:
1. Use the actual title and URL from each document 1. Use the actual title and URL from each document
2. DO NOT use generic placeholders like "Document 1" 2. DO NOT use generic placeholders like "Document 1"
3. Format each reference as: [1] Title of the Article/Page. URL 3. Format each reference as: [1] Title of the Article/Page. URL
4. Make sure all references are complete and properly formatted 4. Each reference MUST include both the title and the URL
5. Number the references sequentially starting from 1"""}, 5. Make sure all references are complete and properly formatted
6. Number the references sequentially starting from 1"""},
{"role": "user", "content": f"""Here are the documents used in the report: {"role": "user", "content": f"""Here are the documents used in the report:
{context} {context}
Create a complete, properly formatted References section in Markdown format."""} Create a complete, properly formatted References section in Markdown format.
Remember to include the URL for EACH reference - this is critical."""}
] ]
references = await self.generate_completion(ref_messages) references = await self.generate_completion(ref_messages)