a few tweaks, fix test & a couple bugs #29
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jkwatson
commented
Nov 21, 2024
| @@ -60,7 +60,8 @@ def __init__( | |||
| api_base=api_base, | |||
| messages_to_prompt=messages_to_prompt, | |||
| completion_to_prompt=completion_to_prompt, | |||
| default_headers=default_headers) | |||
| default_headers=default_headers, | |||
| context=context) | |||
There was a problem hiding this comment.
this fix is actually on main, I think
| @@ -101,6 +95,7 @@ def index_file(self, file_path: str, file_id: str): | |||
|
|
|||
| for chunk, embedding in zip(chunks, embeddings): | |||
| chunk.embedding = embedding | |||
| chunk.metadata["file_name"] = os.path.basename(file_path) | |||
There was a problem hiding this comment.
I'm not sure this is true unless we save with the original file name to s3. I thought we saved with the UUID
| @@ -113,6 +108,7 @@ def _documents_in_file(self, reader: BaseReader, file_path: str, file_id: str) - | |||
|
|
|||
| for i, document in enumerate(documents): | |||
| # Update the document metadata | |||
| document.id_ = file_id | |||
There was a problem hiding this comment.
No need to couple them, right? Is there a reason why we need them to match?
| @@ -124,6 +120,7 @@ def _chunks_in_document(self, document: Document) -> List[BaseNode]: | |||
|
|
|||
| for j, chunk in enumerate(chunks): | |||
| chunk.metadata["file_id"] = document.metadata["file_id"] | |||
| chunk.metadata["document_id"] = document.metadata["file_id"] | |||
There was a problem hiding this comment.
Not sure why? Maybe document_id on both sides?
conradocloudera
added a commit
that referenced
this pull request
Nov 21, 2024
* Provide Indexer to index files * fix imports for local dev * skip tests that require same qdrant client * pass document id within the test * fix the other test with the race condition * fix monkey patch * a few tweaks, fix test & a couple bugs (#29) * resolve mypy * docx support * make ruff happy --------- Co-authored-by: John Watson <jkwatson@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.