feat(vector-stores): add ZeusDB integration #20177
Open
+5,164
−0
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
dosubot
bot
added
the
size:XXL
| ) | ||
|
|
||
| # Try to import the real base, else provide a minimal stub | ||
| try: |
Collaborator
There was a problem hiding this comment.
Why are there so many try/except imports? Generally all these should be covered assuming the pyproject.toml is setup correctly
| else: | ||
| if dim is None: | ||
| raise ValueError("dim is required when not providing zeusdb_index") | ||
| # Defer zeusdb import to runtime |
| ids.append(_id) | ||
| sims.append(_similarity_from_distance(dist, self._space)) | ||
|
|
||
| from llama_index.core.vector_stores.types import ( # type: ignore |
Collaborator
There was a problem hiding this comment.
please avoid nested imports
| # Try real llama_index.core first | ||
| # ---------------------------------------- | ||
| try: | ||
| import llama_index.core.vector_stores.types # type: ignore # noqa: F401 |
Collaborator
There was a problem hiding this comment.
core is a dependency in the toml. Why wouldn't it be installed?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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
This pull request adds the ZeusDB vector store integration to LlamaIndex.
ZeusDB is a high-performance, Rust-powered vector database that provides enterprise-grade retrieval capabilities, product quantization (PQ), and persistent storage.
This integration allows users to leverage ZeusDB within LlamaIndex for scalable and efficient vector storage, retrieval, and querying in RAG pipelines.
Changes
Main package integration files
llama-index-integrations/vector_stores/llama-index-vector-stores-zeusdb→ Includes all required integration files generated from the official LlamaIndex CLI scaffold.
Added new files
docs/examples/vector_stores/ZeusDBIndexDemo.ipynb→ Demonstrates ZeusDB integration and usage through Jupyter Notebook examples.
Modified existing files
docs/src/content/docs/framework/module_guides/storing/vector_stores.mddocs/src/content/docs/framework/community/integrations/vector_stores.md→ Added ZeusDB to the vector store documentation and integration listings.
PyPI Package Alignment
The package is already published on PyPI as
llama-index-vector-stores-zeusdb.The integration code and PyPI package code are fully synchronized with this pull request.
Could you please confirm the PyPI username or organization name associated with the official LlamaIndex account so the package can be transferred to your ownership?
Fixes # (issue): N/A
New Package?
Did I fill in the
tool.llamahubsection in thepyproject.tomland provide a detailed README.md for my new integration or package?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?
Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.
Suggested Checklist:
uv run make format; uv run make lintto appease the lint gods