search

zilliztech / GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
https://gptcache.readthedocs.io
MIT License
7.18k stars 502 forks source link

[Feature]:Support integrate Elasticsearch as the VectorBase #490

Open Qsimple opened 1 year ago

Qsimple commented 1 year ago

Is your feature request related to a problem? Please describe.

Elasticsearch is a distributed, RESTful search and analytics engine. It provides a distributed, multitenant-capable full-text search engine with an HTTP web interface and schema-free JSON documents.

Will gptcache integrate Elasticsearch as the vectorbase?

Describe the solution you'd like.

Implement the gptcache.manager.vector_data.base.VectorBase

Describe an alternate solution.

Implement the gptcache.manager.vector_data.base.VectorBase

Anything else? (Additional Context)

Nothing

SimFG commented 1 year ago

@Qsimple it's a good idea. And if you have free time, you can try to do it. you also try to use the redis, which has supported

AvikantSrivastava commented 1 year ago

@SimFG I am interested in taking up this issue, could you assign it to me?

SimFG commented 1 year ago

@AvikantSrivastava It's fine, thank your contribution!

Qsimple commented 1 year ago

Look forward to review your PR,，;)

AvikantSrivastava commented 1 year ago

Hi @Qsimple @SimFG Sorry for the delay I got a little busy at work, but now I have started working on this issue.

I have raised a PR here https://github.com/zilliztech/GPTCache/pull/509

Currently in WIP, I will add some comments for clarification