forked from phoenix-oss/llama-stack-mirror
a34f3aafcf
# Summary: Right now we would include toolgroup args when we encode messages with tool_calls, which is confusing the model since they not in the function description (see test plan for example). # Test Plan: Add a print statement before raw prompt is sent to providers (no good way to test this currently) Before: ``` cated in the same neighborhood?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[knowledge_search(query="Laleli Mosque and Esma Sultan Mansion same neighborhood", vector_db_ids=["829a68735d744dc3830409dcc782964a"])]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nknowledge_search tool found 5 chunks:\nBEGIN of ``` Note the extra `vector_db_ids` After ``` >user<|end_header_id|>\n\nAre the Laleli Mosque and Esma Sultan Mansion located in the same neighborhood?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[knowledge_search(query="Laleli Mosque and Esma Sultan Mansion same neighborhood")]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nknowledge_search tool found ``` |
||
|---|---|---|
| .. | ||
| inline | ||
| registry | ||
| remote | ||
| tests | ||
| utils | ||
| __init__.py | ||
| datatypes.py | ||