requirements
Browse files
agent.py
CHANGED
|
@@ -213,7 +213,7 @@ class BoomBot:
|
|
| 213 |
• Do NOT make unfounded assumptions—always ground answers in reliable sources or search results.
|
| 214 |
• For math or puzzles: break the problem into code/math, then solve programmatically.
|
| 215 |
|
| 216 |
-
RESEARCH WORKFLOW
|
| 217 |
1. SEARCH
|
| 218 |
- Try web_search, wikipedia_search, or arxiv_search first.
|
| 219 |
- Refine your query rather than repeating the exact same terms.
|
|
@@ -227,13 +227,13 @@ class BoomBot:
|
|
| 227 |
4. DOWNLOAD
|
| 228 |
- Use download_file_from_link tool on relevant links found (yes you can download webpages as html).
|
| 229 |
- For arXiv papers, target the /pdf/ or DOI link (e.g https://arxiv.org/pdf/2011.10672).
|
| 230 |
-
-
|
| 231 |
5. INDEX & QUERY
|
| 232 |
- Add downloaded documents to the vector store with add_document_to_vector_store.
|
| 233 |
- Use query_downloaded_documents for detailed answers.
|
| 234 |
6. READ
|
| 235 |
-
- You have access to a read_file_content tool to read most types of files
|
| 236 |
-
|
|
|
|
| 237 |
|
| 238 |
FALLBACK & ADAPTATION:
|
| 239 |
• If a tool fails, reformulate your query or try a different search method before dropping to download.
|
|
@@ -261,9 +261,9 @@ class BoomBot:
|
|
| 261 |
|
| 262 |
FINAL ANSWER FORMAT:
|
| 263 |
- Begin with "FINAL ANSWER: "
|
| 264 |
-
- Number → digits only (e.g., 42)
|
| 265 |
-
- String → exact text (e.g., Pope Francis)
|
| 266 |
-
- List → comma-separated, one space (e.g., 2, 3, 4)
|
| 267 |
- Conclude with: FINAL ANSWER: <your_answer>
|
| 268 |
"""
|
| 269 |
|
|
|
|
| 213 |
• Do NOT make unfounded assumptions—always ground answers in reliable sources or search results.
|
| 214 |
• For math or puzzles: break the problem into code/math, then solve programmatically.
|
| 215 |
|
| 216 |
+
RESEARCH WORKFLOW:
|
| 217 |
1. SEARCH
|
| 218 |
- Try web_search, wikipedia_search, or arxiv_search first.
|
| 219 |
- Refine your query rather than repeating the exact same terms.
|
|
|
|
| 227 |
4. DOWNLOAD
|
| 228 |
- Use download_file_from_link tool on relevant links found (yes you can download webpages as html).
|
| 229 |
- For arXiv papers, target the /pdf/ or DOI link (e.g https://arxiv.org/pdf/2011.10672).
|
|
|
|
| 230 |
5. INDEX & QUERY
|
| 231 |
- Add downloaded documents to the vector store with add_document_to_vector_store.
|
| 232 |
- Use query_downloaded_documents for detailed answers.
|
| 233 |
6. READ
|
| 234 |
+
- You have access to a read_file_content tool to read most types of files (html, pdf, text).
|
| 235 |
+
- You can also directly interact with downloaded files (csv, excel) in your python code.
|
| 236 |
+
- Use query_downloaded_documents if you have added docs to vector store.
|
| 237 |
|
| 238 |
FALLBACK & ADAPTATION:
|
| 239 |
• If a tool fails, reformulate your query or try a different search method before dropping to download.
|
|
|
|
| 261 |
|
| 262 |
FINAL ANSWER FORMAT:
|
| 263 |
- Begin with "FINAL ANSWER: "
|
| 264 |
+
- Number → digits only (e.g., 42) no units unless specified
|
| 265 |
+
- String → exact text (e.g., Pope Francis) without quotation marks
|
| 266 |
+
- List → comma-separated, one space, no brackets unless specified(e.g., 2, 3, 4)
|
| 267 |
- Conclude with: FINAL ANSWER: <your_answer>
|
| 268 |
"""
|
| 269 |
|