Fixes for add and delete Methods in LanceDBVectorStore #11825
Merged
Conversation
This file contains 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
dosubot
bot
added
the
size:XS
hatianzhang
approved these changes
Mar 11, 2024
bdonkey
added a commit
to bdonkey/gpt_index
that referenced
this pull request
Mar 12, 2024
* main: add retries for openai LLM rate limit errors (run-llama#11867) Fix stream chat param error in CondenseQuestionChatEngine (run-llama#11856) Add logprobs field to `CompletionResponse` (run-llama#11855) Google readers integrations doc and drive updates (run-llama#11724) Adds llamafile support for local LLM and embeddings (run-llama#11709) Add QueryUnderstandingAgent LlamaPack (run-llama#11558) Split Google docs on headings (run-llama#11535) add baidu vectordb as vector store (run-llama#11494) [Feature Request]: add PowerPoint support to Confluence reader run-llama#10592 (run-llama#11454) add modelscope llm support (run-llama#11270) Add cohere command-R model (run-llama#11852) Fixed some gramatical mistakes (run-llama#11840) fix obj insert_nodes (run-llama#11836) added table comment to Table Info in SQLDatabase (run-llama#11774) Fixes for add and delete Methods in LanceDBVectorStore (run-llama#11825) add support for open-mixtral-8x7b (run-llama#11792) Adds new LabelledSimpleDataset (llama-dataset) (run-llama#11805) Fix Cohere Embeddings issue run-llama#11820 (run-llama#11822) Update verifying connection (run-llama#11821) bump mistralai deps (run-llama#11819)
Izukimat
pushed a commit
to Izukimat/llama_index
that referenced
this pull request
Mar 29, 2024
fix: Fixes for add and delete Methods in LanceDBVectorStore
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Outdated suggestions cannot be applied.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.
Description
Two fixes to the LanceDBVectorStore class. These fixes address issues encountered when invoking the add method with an empty list and using an incorrect field name in the delete method. I encountered this errors while using LanceDB with Ingestion Pipeline + Document Management (similar to this but with LanceDB vector store), when the ingestion pipeline tries to apply the changes in documents to the vector database.
I've created this Colab to reproduce the issues:
https://colab.research.google.com/drive/1F-3NNPv1zcJLA6NDdE2QtaqAuF3V5P1F?usp=sharing
Handling Empty List in add Method
Invoking add([]) leads to an IndexError due to an attempt to access the first element of an empty list in the . Added a check at the beginning of the add method to return early if the input list is empty.
Correcting Field Name in delete Method
The delete method uses an incorrect field name (document_id) for deletion, the field name is set here, when deleting it should use the same field name.
Version Bump?
Did I bump the version in the
pyproject.tomlfile of the package I am updating? (Except for thellama-index-corepackage)Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Suggested Checklist:
make format; make lintto appease the lint gods