chroma
chroma copied to clipboard
Open-source search and retrieval database for AI applications.
### What happened? I have tried to remove the ids from the index which are non-existent, after that every `peek()` operation causes the warning `Delete of nonexisting embedding ID`. @HammadB...
## Description of changes *Summarize the changes made by this PR.* - New functionality Introduces the orchestrator for count and a basic counting logic where we simply add the number...
## Description of changes *Summarize the changes made by this PR.* - Improvements & Bug fixes - This PR pass in allowed_ids and disallowed_ids to HNSW bindings. - New functionality...
### What happened? I'm having some serious useability problmes with this embedding limit. I had it on upsert, where i think it is understandable somewhat. I have chunked it as...
## Description of changes *Summarize the changes made by this PR.* - New functionality - Migrate the full-text search index to the new reader/writer pattern and add some tests. ##...
### Describe the problem It would be good to keep things up to date. However it was blocking https://github.com/chroma-core/chroma/pull/2107 and I needed to land it. ### Describe the proposed solution...
### What happened? Chromadb will fail to return the embeddings with the closest results unless I set n_results to a sufficiently large number. I am using version 0.4.22 but this...
### What happened? I have a very simple query: ``` results = self.chroma.query( query_embeddings=self.embedder(query), # calls embedder here ) print(len(results["ids"][0])) ``` It outputs: ``` 12 ``` The documentation here says...
## Description of changes *Summarize the changes made by this PR.* - Improvements & Bug fixes - Removed unnecessary complex way of importing openai lib - Added extra error handling...
### Describe the problem Currently we only set the `ef_search` parameter when we init the index, usually on creation of a `Collection`. However, this parameter is actually per-query at the...