Add the new Agent Powered Retrieval notebook #253
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
| @@ -0,0 +1,1200 @@ | |||
| { | |||
There was a problem hiding this comment.
if len(retrieved_documents.get("documents")) > top_k:
can be removed.
retrieved_documents["documents"] = retrieved_documents["documents"][:top_k]
should always work if top_k is an integer
Reply via ReviewNB
| @@ -0,0 +1,1200 @@ | |||
| { | |||
There was a problem hiding this comment.
Line #6. top_k: Optional[int] = 5
Optional[int] means Union[int, None].
Since the function breaks if top_k is None, I would use top_k: int=5
Reply via ReviewNB
| @@ -0,0 +1,1200 @@ | |||
| { | |||
There was a problem hiding this comment.
As far as I can understand, here we are using the JSON schema mostly to accurately describe the metadata_filters that we consider valid in this case. Right? If so, I'd add that in several other cases, you don't need to manually specify the JSON schema but can use @tool/create_tool_from_function
Reply via ReviewNB
|
Nice! Left some comments. |
Uh oh!
There was an error while loading. Please reload this page.