search

torvalds-dev / llama_index

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
https://docs.llamaindex.ai
MIT License
0 stars 0 forks source link

[Feature Request]: Feature Description I would like to add support for GCP Matching Engine as a vector store. #11

Open Raghavan1988 opened 10 months ago

Raghavan1988 commented 10 months ago

Feature Description

Feature Description

I would like to add support for GCP Matching Engine as a vector store. Reason

I don't see GCP listed in https://github.com/run-llama/llama_index/tree/main/llama_index/vector_stores . We would have to write a custom vector store, but I feel like it could be include in the repo. Value of Feature

Allow Google Cloud Users to easily integrate with Llamaindex

Reason

No response

Value of Feature

No response

torvalds-dev commented 10 months ago

torvalds.dev is analyzing the ticket

torvalds-dev commented 10 months ago

The issue is a feature request to add support for Google Cloud Platform (GCP) Matching Engine as a vector store in the Llama Index project. The user has noticed that GCP is not listed in the vector stores of the project and believes that adding it would allow Google Cloud users to easily integrate with Llama Index.

To address this issue, the following actions should be taken:

  1. Understand the structure and functionality of existing vector stores in the Llama Index project. This can be done by reviewing the code and documentation of the existing vector stores.

  2. Research and understand how GCP Matching Engine works, its API, and how it can be used as a vector store.

  3. Design and implement a new vector store for GCP Matching Engine following the structure and conventions of the existing vector stores in the Llama Index project.

  4. Test the new vector store with GCP Matching Engine to ensure it works correctly and efficiently.

  5. Document the new vector store, explaining how it works and how to use it.

  6. Submit a pull request to the Llama Index project with the new vector store for GCP Matching Engine.

The relevant files to this issue are:

  1. llama_index/vector_stores/cogsearch.py: This file contains the implementation of the Azure Cognitive Search vector store. It can be used as a reference for implementing the GCP Matching Engine vector store.

  2. llama_index/vector_stores/__init__.py: This file lists all the vector stores supported by the Llama Index project. The new GCP Matching Engine vector store should be added to this list once it's implemented.

  3. llama_index/indices/vector_store/__init__.py: This file contains the vector-store based data structures. It might need to be updated depending on the requirements of the GCP Matching Engine vector store.

  4. llama_index/indices/managed/types.py: This file contains the vector store index types. It might need to be updated depending on the requirements of the GCP Matching Engine vector store.