chroma

chroma copied to clipboard

## Description of changes The [OpenAI documentation](https://platform.openai.com/docs/guides/rate-limits/error-mitigation) warns that "the response object may not return completions in the order of the prompts, so always remember to match responses back to...

ashwinsr

Update with duplicate IDs fails

7

Because `add` allows duplicate / redundant IDs. When `update` gets called and finds redundant IDs, it fails with an obtuse error. This is an artifact of allowing redundant IDs, we...

atroyn

Index not found after using it

3

I used chromadb to embed and index some data, but randomly after being used, I started getting Index not found : `WARNING:root:Collection langchain already exists, Do you have the right...

aymanek

Bug: querying collection when no data added causes crash

3

trivial example is 1. https://colab.research.google.com/drive/1QEzFyqnoFxq7LUGyP1vzR4iLt9PpCDXv?usp=sharing#scrollTo=64dWyeEdKAX9 2. comment out `collection.add` 3. run all cells 

swyxio

Remove sentence-transformers as a hard requirement

8

Currently we use `sentence-transformers` as the default embedding model. However this means that it, and a lot of it's deps are included in the project. Additionally it downloads the model...

jeffchuber

default setting for persist_directory leads to ValueError

2

```Using embedded DuckDB with persistence: data will be stored in: .chroma Traceback (most recent call last): File "/Users/patrickgerard/Documents/GitHub/AI-video-genie/src/main.py", line 99, in genius = Genius() File "/Users/patrickgerard/Documents/GitHub/AI-video-genie/src/main.py", line 19, in __init__...

grumpyp

Persist directory

1

fixes #338

grumpyp

Inconsistent behaviour when filtering by metadata using $or

3

Hi, i'm running into a problematic behaviour with querying chroma using **$or** on metadata from python: Given a collection with a set of embeddings where the metadata contains information like...

UlliBe

Persistent DB

3

Data persistence behavior does not seem aligned with what folks may expect given other DBs. For example, if I make a MongoDB data/db folder for development, I can connect and...

mxchinegod

Indexing with 1M random vector is slow

8

``` # %% import chromadb client = chromadb.Client() # %% import numpy as np from tqdm import tqdm # %% from chromadb.api.types import Documents, EmbeddingFunction, Embeddings class MyEmbeddingFunction(EmbeddingFunction): def __call__(self,...

junwang-wish