Reason of this fork

By default, Chroma does not perform exact search but use HNSW, to perform approximate neighbor search. The issue is that, as discussed here, the default parameters can be quite bad, resulting in really bad results unless n_results is large enough. Returning more results gives better results because the number of searched element is scaled depending on max(search_ef, n_returns). To get better results without returning a lot of elements, one can simply scale the hnsw:search_ef parameter in the DB metadata during creation: collection_chroma = chroma_client.create_collection(name="db_name", metadata={"hnsw:space": "cosine", "hnsw:search_ef": 512}).

However, once created, editing this parameter is hard (the collection.modify() modifies it, but is not compatible with keeping cosine distance and does not seems to work). The proposed (not optimal) fix is to hard-set this value during the loading of the index.

Chroma - the open-source embedding database.
The fastest way to build Python or JavaScript LLM apps with memory!

| | Docs | Homepage

|

pip install chromadb # python client
# for javascript, npm install chromadb!
# for client-server mode, chroma run --path /chroma_db_path

The core API is only 4 functions (run our 💡 Google Colab or Replit template):

import chromadb
# setup Chroma in-memory, for easy prototyping. Can add persistence easily!
client = chromadb.Client()

# Create collection. get_collection, get_or_create_collection, delete_collection also available!
collection = client.create_collection("all-my-documents")

# Add docs to the collection. Can also update and delete. Row-based API coming soon!
collection.add(
    documents=["This is document1", "This is document2"], # we handle tokenization, embedding, and indexing automatically. You can skip that and add your own embeddings as well
    metadatas=[{"source": "notion"}, {"source": "google-docs"}], # filter on these!
    ids=["doc1", "doc2"], # unique for each doc
)

# Query/search 2 most similar results. You can also .get by id
results = collection.query(
    query_texts=["This is a query document"],
    n_results=2,
    # where={"metadata_field": "is_equal_to_this"}, # optional filter
    # where_document={"$contains":"search_string"}  # optional filter
)

Features

• Simple: Fully-typed, fully-tested, fully-documented == happiness
• Integrations: 🦜️🔗 LangChain (python and js), 🦙 LlamaIndex and more soon
• Dev, Test, Prod: the same API that runs in your python notebook, scales to your cluster
• Feature-rich: Queries, filtering, density estimation and more
• Free & Open Source: Apache 2.0 Licensed

Use case: ChatGPT for ______

For example, the "Chat your data" use case:

1. Add documents to your database. You can pass in your own embeddings, embedding function, or let Chroma embed them for you.
2. Query relevant documents with natural language.
3. Compose documents into the context window of an LLM like GPT3 for additional summarization or analysis.

Embeddings?

What are embeddings?

• Read the guide from OpenAI
• Literal: Embedding something turns it from image/text/audio into a list of numbers. 🖼️ or 📄 => [1.2, 2.1, ....]. This process makes documents "understandable" to a machine learning model.
• By analogy: An embedding represents the essence of a document. This enables documents and queries with the same essence to be "near" each other and therefore easy to find.
• Technical: An embedding is the latent-space position of a document at a layer of a deep neural network. For models trained specifically to embed data, this is the last layer.
• A small example: If you search your photos for "famous bridge in San Francisco". By embedding this query and comparing it to the embeddings of your photos and their metadata - it should return photos of the Golden Gate Bridge.

Embeddings databases (also known as vector databases) store embeddings and allow you to search by nearest neighbors rather than by substrings like a traditional database. By default, Chroma uses Sentence Transformers to embed for you but you can also use OpenAI embeddings, Cohere (multilingual) embeddings, or your own.

Get involved

Chroma is a rapidly developing project. We welcome PR contributors and ideas for how to improve the project.

• Join the conversation on Discord - #contributing channel
• Review the 🛣️ Roadmap and contribute your ideas
• Grab an issue and open a PR - Good first issue tag
• Read our contributing guide

Release Cadence We currently release new tagged versions of the pypi and npm packages on Mondays. Hotfixes go out at any time during the week.

License

Apache 2.0