This release is a pre-release and may not be stable for production use.
Chroma
Chroma is the open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs.
ChatGPT for ______
For example, the "Chat your data" use case:
- Add documents to your database. You can pass in your own embeddings, embedding function, or let Chroma embed them for you.
- Query relevant documents with natural language.
- Compose documents into the context window of an LLM like
GPT3for additional summarization or analysis.
Features
- Simple: Fully-typed, fully-tested, fully-documented == happiness
- Integrations:
🦜️🔗 Langchainand🦙 gpt-index - 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: Apache 2.0 Licensed
Get up and running
pip install chromadb
import chromadb
client = chromadb.Client()
collection = client.create_collection("all-my-documents")
collection.add(
embeddings=[[1.5, 2.9, 3.4], [9.8, 2.3, 2.9]],
metadatas=[{"source": "notion"}, {"source": "google-docs"}],
ids=["n/102", "gd/972"],
)
results = collection.query(
query_embeddings=[1.5, 2.9, 3.4],
n_results=3
)
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
- Review the roadmap and contribute your ideas
- Grab an issue and open a PR
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.
License
Metadata
Release files for chromadb 0.0.3.dev332
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| chromadb-0.0.3.dev332.tar.gz | 35.4 kB | Without provenance | Details for chromadb-0.0.3.dev332.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| chromadb-0.0.3.dev332-py3-none-any.whl | Python 3 | none | any | Details for chromadb-0.0.3.dev332-py3-none-any.whl |
Total release size: 67.7 kB
Release files / chromadb-0.0.3.dev332.tar.gz
| Download URL | chromadb-0.0.3.dev332.tar.gz |
|---|---|
| Size | 35.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d60267c40dcb592c305501a3ee4be8f1d89d06ab02c0ad312e8c381722e6d2be
|
|
BLAKE2b-256 checksum How to use checksums |
cb4db7aa9f24fb2f7e8350a74d3fa37acc74c842e3313f855f5a4ddb97d7212a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.8
|
Release files / chromadb-0.0.3.dev332-py3-none-any.whl
| Download URL | chromadb-0.0.3.dev332-py3-none-any.whl |
|---|---|
| Size | 32.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ed170c47df437106e64aaf4f1495861ae0a3c32ffff49a23dfc81f3c6452c2eb
|
|
BLAKE2b-256 checksum How to use checksums |
ff77b4727cb9a7bc2d91533e8f00ce205684b5fe703fe1f705c2fdb4913fa9f2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.8
|
Security for chromadb 0.0.3.dev332
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.