ChromaDB
Chroma is an open-source vector database for storing and querying embedding vectors and associated data, such as documents and metadata.
Grokking AI Applications
Chroma is an open-source vector database for storing embeddings and associated data and performing similarity-based retrieval.
- How it is used
- Builds the local vector-store layer of a RAG pipeline for ingesting document chunks and retrieving relevant context.
- How deep it goes
- Configures collections, disk persistence, ingestion, and top-match retrieval, without descending into vector-database internals.
- Examples
- Uses a pizzeria menu PDF, overlapping text chunks, a menu collection, and a menu persistence directory.
- What you can do after
- Build it from scratch as a local Chroma-backed RAG ingestion and retrieve-and-generate pipeline.
Generative AI in Action
Chroma is an open-source vector database for storing and querying embeddings and their associated documents or metadata.
- How it is used
- Stores document text and embeddings for semantic retrieval in a question-answering application.
- How deep it goes
- Demonstrates persistence and Semantic Kernel integration without detailing database internals.
- Examples
- Uses extracted PDF pages, an OpenAI embedding service, and a locally configured Chroma memory store.
- What you can do after
- Apply it via Semantic Kernel to persist document embeddings for semantic retrieval.
AI Agents and Applications
Chroma is a vector database that stores text, embeddings, and metadata and supports similarity-based retrieval.
- How it is used
- Provides the vector store for semantic search and document Q&A in a retrieval-augmented generation pipeline.
- How deep it goes
- Walks through collection setup, ingestion, querying, and client options, while deferring advanced chunking considerations.
- Examples
- Uses Paestum passages and a Doric-temple question, then ingests Wikipedia, Word, PDF, and text documents.
- What you can do after
- Apply it via Chroma and LangChain to store document chunks and retrieve relevant passages for a Q&A chatbot.
AI Agents in Action, Second Edition
Chroma DB is a database system for storing and retrieving vector embeddings and associated document data.
- How it is used
- Supports local semantic document retrieval for development, small-scale projects, and vector-search RAG agents.
- How deep it goes
- Explains chunking, embedding, collection persistence, querying, result fields, and cosine-distance interpretation without covering larger deployment options in detail.
- Examples
- Uses document collections, a movie script, queries such as “lazy dog,” and exercises that persist vectors and test vector-only RAG retrieval.
- What you can do after
- Build a local Chroma DB collection, persist embeddings, query semantic matches, and inspect returned IDs, distances, and document text.
Read how AI Agents in Action, Second Edition explains ChromaDB →
Data Storytelling with Altair and AI
Chroma is an embedding database for storing and retrieving vector representations of data.
- How it is used
- Supports retrieval-augmented generation by storing embedded source content for downstream language-model queries.
- How deep it goes
- Explains loading, chunking, embedding, persistence, retrieval, and output, without detailing Chroma's internal indexing.
- Examples
- Uses an HTML smartphone description, a Product-Info collection, and a generated SmartX 2023 answer with source documents.
- What you can do after
- Build it from scratch by persisting embedded documents in Chroma and querying them through a LangChain retrieval application.
Read how Data Storytelling with Altair and AI explains ChromaDB →
Effective Conversational AI
Chroma is an open-source vector database and retrieval system for storing and searching embedding vectors.
- How it is used
- Supports RAG by storing embedded document chunks and retrieving semantically similar passages for response generation.
- How deep it goes
- Explains chunking, embedding, storage, and retrieval, while noting alternative retrieval methods and model-dependent performance.
- Examples
- Uses text files, chunking experiments, open-source embeddings, Chroma ingestion, and a LangChain example.
- What you can do after
- Build it from scratch by chunking sample text, embedding chunks, and loading them into Chroma for retrieval experiments.
Build Applications with Local AI Models on a Mac
ChromaDB is an open-source vector database for storing, querying, and managing embeddings and associated data.
- How it is used
- Uses ChromaDB to retrieve relevant documents for a RAG response.
- How deep it goes
- Demonstrates creating a collection, adding documents, and finding close matches without detailing database internals.
- Examples
- Uses short documents about Ollama, Streamlit, RAG, and other AI tools, then retrieves an answer about Ollama.
- What you can do after
- Apply ChromaDB by creating a collection, adding documents, and retrieving relevant matches in a RAG example.
Read how Build Applications with Local AI Models on a Mac explains ChromaDB →
Also covered in
What to know first
- embeddingAn embedding is a numerical vector representation of an item in a feature space, encoding selected properties or relationships for computational tasks such as comparison or retrieval.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- vector databaseA vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
- knowledge baseA knowledge base is an organized body or representation of information that people or computational systems can consult to support retrieval, reference, reasoning, or tasks.
Related concepts
- vector databasekind of · A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
- retrieval-augmented generationused by · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- conversational aiused by · Conversational AI is artificial intelligence that enables software systems to interpret user input and interact with users through natural-language dialogue.
- FAISSalternative to · FAISS is an open-source software library for efficient similarity search and clustering of dense vectors.
- collectionuses · A collection is a container or abstraction that groups multiple elements for storage, access, traversal, or processing.
- embeddingused by · An embedding is a numerical vector representation of an item in a feature space, encoding selected properties or relationships for computational tasks such as comparison or retrieval.
Questions about ChromaDB
What is ChromaDB?
Chroma is an open-source vector database for storing and querying embedding vectors and associated data, such as documents and metadata.
Which Manning books explain ChromaDB?
Grokking AI Applications, Generative AI in Action, AI Agents and Applications, AI Agents in Action, Second Edition, Data Storytelling with Altair and AI, Effective Conversational AI and Build Applications with Local AI Models on a Mac.
What should I know before learning ChromaDB?
Manning books that teach ChromaDB usually introduce embedding, language model, vector database and knowledge base first.
What is the difference between ChromaDB and FAISS?
Chroma is an open-source vector database for storing and querying embedding vectors and associated data, such as documents and metadata. FAISS is an open-source software library for efficient similarity search and clustering of dense vectors.
What is ChromaDB a kind of?
ChromaDB is a kind of vector database. A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
What is ChromaDB also called?
ChromaDB is also called Chroma.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.






