chroma
chroma copied to clipboard
Open-source search and retrieval database for AI applications.
### What happened? I'm using uv to install and run a Python project. The `pyproject.toml` is shown below. I use `uv sync` to create the virtual environment and install all...
### What happened? Related: #4346 ## Description In addition to the observation in #4346 that document ID can be empty string, I found some edge cases that we may wish...
## Description of changes This PR adds support to convert both get and query results to pandas dataframes. As a byproduct, users can now get results in row format. ##...
## Description of changes This PR uses the default space defined for an embedding function if available, closes https://github.com/chroma-core/chroma/issues/2128 ## Test plan *How are these changes tested?* - [ ]...
### What happened? I have more than 20 millions records on the chromadb. The chroma is deployed as a server on docker. While executing below query query_params = {"query_embeddings": query_embeddings,...
## Description of changes *Summarize the changes made by this PR.* - Improvements & Bug fixes - ... - New functionality - ... ## Test plan *How are these changes...
## Description of changes This PR adds python client and async python client support to query on a filtered set of IDs example: ``` ids = ["1", "2", "3"] documents...
## Description of changes *Summarize the changes made by this PR.* - Improvements & Bug fixes - ... - New functionality - ... ## Test plan *How are these changes...
## Description of changes Following up on #4280 Adds some details about the filters, making clear that: * filter dictionaries must have one key * `$in`/`$nin` lists must contain one...
## Description of changes _Summarize the changes made by this PR._ - Improvements & Bug fixes - Spann has rust tests that take longer than usual tests (4-5 mins). Running...