Frequently Asked Questions and Commonly Encountered Issues Frequently Asked Questions What does Chroma use to index embedding vectors? How to set dimensionality of my collections?...

Embedding Functions GPU Support Default Embedding Functions (Onnxruntime) Sentence Transformers OpenCLIP Embedding Functions GPU Support By default, Chroma does not require G...

Batching Creating Batches Batching It is often that you may need to ingest a large number of documents into Chroma. The problem you may face is related to the underlying SQLite...

Memory Management LRU Cache Strategy Manual/Custom Collection Unloading Memory Management This section provided additional info and strategies how to manage memory in Chroma. ...

Collections Collection Basics Collection Properties Creating a collection Deleting a collection Listing all collections Getting a collection Modifying a collection Counting C...

LlamaIndex Embeddings Embedding Functions LlamaIndex Embeddings Embedding Functions Chroma and LlamaIndex both offer embedding functions which are wrappers on top of popular e...

Langchain Embeddings Embedding Functions Chroma Built-in Langchain Adapter Custom Adapter Example Usage Langchain Embeddings Embedding Functions Chroma and Langchain both o...

Chroma Ecosystem Clients Python JavaScript Ruby Client Java Client Go Client C# Client Rust Client Elixir Client Dart Client PHP Client PHP (Laravel) Client Chroma Ec...

Cross-Encoders Reranking Hugging Face Cross Encoders Cross-Encoders Reranking Work in Progress This page is a work in progress and may not be complete. For now this is just a...

Keyword Search Keyword Search Chroma uses SQLite for storing metadata and documents. Additionally documents are indexed using SQLite FTS5 for fast text search. import chr...