-
## Problem
With the advancement of AI tools, it's becoming increasingly useful to work with embeddings/vectors
## Suggested solution
Support the pg_vector type
https://github.com/pgvector/…
-
Now the AI time every database begin support vector. Vector for embedding is the key to RAG/Chat.
wizd updated
3 months ago
-
- [x] plan tree 没有改写 target list 的内容，columns 字段里没有东西
- [x] explain 语句实现了吗？ok
- [ ] physical plan 字段中的 logical plan 和 logical query 是什么区别
- [ ] 从redo 中恢复数据的能力，从 undo 中回滚数据的能力，以及checkpoint
- [ ] 增加自…
-
I looked into the code, segcore_wrapper always create Growing segment, and growing segment only use brute-force in search?
If it's true, do you have plan to support different index type.
-
I think this feature would make a lot of sense.
I can add an `"images"` field in requests to `/api/generate` when using a multi-modal model, why can't I do the same for requests to `/api/embeddings`?…
-
Issue to track efforts towards setting up a Postgres backend DB.
https://github.com/Azure-Samples/rag-postgres-openai-python
https://github.com/Azure-Samples/rag-postgres-openai-python/blob/e30ea9…
-
Hi @frdel, thanks for your great work!
I found AutoMemory to be quite inefficient because it produces a summarization of the same memories at every step of the conversation.
### Suggestion
My…
-
[Kúzu](https://kuzudb.com/) is an embedded graph database. We want to explore graph-RAG capabilites to include more relevant information when retrieving semantically.
A good MVP for this would be m…
-
### The bug
When lots of pictures occurred on the day of the memory (2 years ago today, etc), the 'progress' bar and counter are not loaded correctly:
2. Weighted-keywords search
In both cases, we can have a sparse vector representation:…