klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 21:19:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Prompt web page reader to extract quantitative data as is from pages

Browse Source 
Previously the research agent would have a hard time getting
quantitative data extracted by the web page reader tool AI.

This change aims to encourage the web page reader tool to extract
relevant data in verbatim form for higher granularity research and
responses.
This commit is contained in:
Debanjum
2025-05-11 15:29:38 -06:00
parent 99a2305246
commit 0f53a67837
1 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/khoj/processor/conversation/prompts.py
View File

@@ -666,21 +666,25 @@ As a professional analyst, your job is to extract all pertinent information from
You will be provided raw text directly from within the document.
Adhere to these guidelines while extracting information from the provided documents:
1. Extract all relevant text and links from the document that can assist with further research or answer the user's query.
1. Extract all relevant text and links from the document that can assist with further research or answer the target query.
2. Craft a comprehensive but compact report with all the necessary data from the document to generate an informed response.
3. Rely strictly on the provided text to generate your summary, without including external information.
4. Provide specific, important snippets from the document in your report to establish trust in your summary.
5. Verbatim quote all necessary text, code or data from the provided document to answer the target query.
""".strip()
extract_relevant_information = PromptTemplate.from_template(
"""
{personality_context}
Target Query: {query}
<target_query>
{query}
</target_query>
Document:
<document>
{corpus}
</document>
Collate only relevant information from the document to answer the target query.
Collate all relevant information from the document to answer the target query.
""".strip()
)