ChromaDB
ChromaDB is an open-source vector database designed for AI applications and large language model scenarios. It supports storing, indexing, and querying high-dimensional vector embeddings, enabling efficient semantic similarity search. ChromaDB offers both local deployment and cloud-based operating modes, with interfaces for mainstream programming languages including Python and JavaScript. It is commonly used in building retrieval-augmented generation (RAG) systems, semantic search, and long-term memory management applications.
Core Facts
RAG（检索增强生成）技术架构将文档切片、向量化、存入向量数据库，查询时先检索相关片段再交给模型生成回答
Agent的记忆系统通常分为三个层次：工作记忆（当前对话上下文窗口）、短期记忆（近期交互历史）和长期记忆（通过向量数据库持久化存储）
Vector databases (such as ChromaDB, Milvus, and Pinecone) use indexing algorithms such as HNSW and IVF to achieve millisecond-level retrieval among millions or even hundreds of millions of vectors.
Timeline (last 90 days)
ScopeGuard's AI pipeline includes Ollama local LLM inference, ChromaDB vector retrieval, SentenceTransformers local embeddings, a deterministic NLP fallback engine and a deterministic pricing engine.
The hands-on project's tech stack includes ChromaDB, the all-MiniLM-L6-v2 embedding model, a weather service built on FastMCP, and the Claude model called via the Anthropic API.
Boge calls RAG "a relatively common and low-cost solution in enterprises," and the course will lead learners through a complete implementation of the RAG workflow in Java code, involving vector databases such as ChromaDB and Milvus.
Once an embedding model is determined, it cannot be changed midway, otherwise the newly written vectors will be inconsistent in dimension with the old vectors, ChromaDB will report an error, and all historical data can only be rebuilt.
RecallOS is a local AI document memory and search assistant based on Python, relying on Streamlit, Ollama and ChromaDB.
ChromaDB's semantic search uses nearest-neighbor retrieval, by default using cosine similarity, supports specifying top-k with n_results, and supports where metadata filtering.
Chat history can be stored in SQLite and searched with FTS5 full-text indexing; it can also be embedded and stored in another collection in ChromaDB, but care must be taken to distinguish the document collection from the conversation collection to avoid retrieval contamination.
The motivation for the localization refactor is privacy: the terminal application confines data flow to the local process, with Ollama and Sentence Transformers doing local inference and ChromaDB persisting locally to disk.
On an Apple M4 (16GB memory), running all-MiniLM-L6-v2 through ChromaDB embedded 50,000 documents in 161.6 seconds (309 per second), with no dedicated GPU required.
The system selects different persistence technologies based on access patterns, adopting a hybrid storage approach combining ChromaDB, JSONL, and SQLite.
3 more timeline events
All Facts (20)
RAG（检索增强生成）技术架构将文档切片、向量化、存入向量数据库，查询时先检索相关片段再交给模型生成回答
90%VerifiedAgent的记忆系统通常分为三个层次：工作记忆（当前对话上下文窗口）、短期记忆（近期交互历史）和长期记忆（通过向量数据库持久化存储）
80%VerifiedVector databases (such as ChromaDB, Milvus, and Pinecone) use indexing algorithms such as HNSW and IVF to achieve millisecond-level retrieval among millions or even hundreds of millions of vectors.
80%Verified常见的向量数据库包括ChromaDB、Milvus、Pinecone、Weaviate，它们针对高维向量的近似最近邻（ANN）搜索进行了专门优化
80%Verified长期记忆Agent通常基于RAG（检索增强生成）技术构建，通过向量数据库将信息转化为高维向量并持久化存储
80%VerifiedChromaDB is an open-source vector database that supports multiple similarity calculation methods such as cosine similarity and Euclidean distance, and provides persistent storage and metadata filtering capabilities.
70%VerifiedRAG (Retrieval-Augmented Generation) typically comprises three core components: a vector database, a retriever (which recalls relevant document chunks based on cosine similarity), and a generator.
65%VerifiedChromaDB is an open-source embedded vector database designed specifically for AI applications, released in late 2022.
65%VerifiedChromaDB is an open-source embedded vector database that can run entirely locally without a network connection.
65%UnverifiedOpen WebUI 内置了完整的 RAG 流水线，用户无需单独部署 ChromaDB 或 Milvus 等向量数据库
90%UnverifiedAutoGPT通过向量数据库（如Pinecone、ChromaDB等）实现长期记忆，突破LLM上下文窗口限制
85%Partially VerifiedAnythingLLM has built-in support for multiple vector databases including ChromaDB, Pinecone, LanceDB, and Weaviate.
80%UnverifiedChromaDB与Pinecone、Milvus、Weaviate等生产级向量数据库相比，更适合原型开发和中小规模应用
80%UnverifiedScopeGuard's AI pipeline includes Ollama local LLM inference, ChromaDB vector retrieval, SentenceTransformers local embeddings, a deterministic NLP fallback engine and a deterministic pricing engine.
50%UnverifiedThe hands-on project's tech stack includes ChromaDB, the all-MiniLM-L6-v2 embedding model, a weather service built on FastMCP, and the Claude model called via the Anthropic API.
50%UnverifiedBoge calls RAG "a relatively common and low-cost solution in enterprises," and the course will lead learners through a complete implementation of the RAG workflow in Java code, involving vector databases such as ChromaDB and Milvus.
50%UnverifiedThe motivation for the localization refactor is privacy: the terminal application confines data flow to the local process, with Ollama and Sentence Transformers doing local inference and ChromaDB persisting locally to disk.
50%UnverifiedRecallOS is a local AI document memory and search assistant based on Python, relying on Streamlit, Ollama and ChromaDB.
50%UnverifiedOnce an embedding model is determined, it cannot be changed midway, otherwise the newly written vectors will be inconsistent in dimension with the old vectors, ChromaDB will report an error, and all historical data can only be rebuilt.
50%UnverifiedChromaDB's semantic search uses nearest-neighbor retrieval, by default using cosine similarity, supports specifying top-k with n_results, and supports where metadata filtering.
50%