Vector Databases & Embeddings

Pinecone, Weaviate, pgvector. How to store and search embeddings for production AI apps.

10·Free resources

0 of 10 resources completed

Log in to track progress

Log in to mark resources complete and sync progress across devices.

  • Docs25 min

    Pinecone - Vector database fundamentals

    Indexes, namespaces, and hybrid search patterns.

    Open resource
  • Docs22 min

    Weaviate - Schema and vectorizer setup

    GraphQL APIs and modular embeddings.

    Open resource
  • Docs28 min

    pgvector - Postgres extension

    Store embeddings next to relational data for RAG.

    Open resource
  • Docs30 min

    Milvus - Architecture overview

    Sharding, replication, and billion-scale vectors.

    Open resource
  • Docs18 min

    OpenAI - Embeddings guide

    Dimensions, similarity metrics, and batching costs.

    Open resource
  • Article20 min

    Anthropic - Embeddings & retrieval

    Pairing Claude with your own vector stores.

    Open resource
  • Docs24 min

    Qdrant - Filtering and payloads

    Metadata filters for production retrieval.

    Open resource
  • Docs26 min

    LangChain - Vector store integrations

    Swap backends without rewriting application code.

    Open resource
  • Article35 min

    FAISS - Facebook AI similarity search

    When to run in-process indexes vs managed services.

    Open resource
  • Docs30 min

    Elastic - Vector search in Elasticsearch

    Hybrid lexical + dense retrieval in one cluster.

    Open resource

← All learning paths