# Weave

> Documentation for Weave, version 1.x.
> Every entry links to the page's markdown source.

Repository: https://github.com/xraph/weave
Site: https://www.xraph.com/docs/weave

## Pages

- [Go Packages](https://www.xraph.com/docs/weave/api-reference/go-packages.md): Quick reference for all Weave Go packages and their public APIs.
- [HTTP API Reference](https://www.xraph.com/docs/weave/api-reference/http-api.md): Complete reference for all 12 Weave REST endpoints — collections, documents, retrieval, and search.
- [Architecture](https://www.xraph.com/docs/weave/architecture.md): How Weave's packages fit together.
- [Configuration](https://www.xraph.com/docs/weave/concepts/configuration.md): Options and defaults for engine.New and the Forge extension.
- [Entities](https://www.xraph.com/docs/weave/concepts/entities.md): The core data types in Weave — Collection, Document, and Chunk.
- [Error Handling](https://www.xraph.com/docs/weave/concepts/errors.md): Sentinel errors returned by Weave operations.
- [Identity (TypeID)](https://www.xraph.com/docs/weave/concepts/identity.md): How Weave uses prefix-qualified, globally unique identifiers for every entity.
- [Multi-Tenancy](https://www.xraph.com/docs/weave/concepts/multi-tenancy.md): How Weave scopes collections, documents, and chunks to app and tenant contexts.
- [Getting Started](https://www.xraph.com/docs/weave/getting-started.md): Install Weave and ingest your first document in under five minutes.
- [Custom Components](https://www.xraph.com/docs/weave/guides/custom-store.md): Implement custom Chunker, Embedder, Loader, and VectorStore to plug your own backends into Weave.
- [Forge Extension](https://www.xraph.com/docs/weave/guides/forge-extension.md): Mount Weave into a Forge application as a first-class extension with automatic route registration and migrations.
- [End-to-End RAG Pipeline](https://www.xraph.com/docs/weave/guides/full-example.md): Complete walkthrough — create a collection, ingest documents, retrieve context, and build a prompt for an LLM.
- [Multi-Tenant Guide](https://www.xraph.com/docs/weave/guides/gdpr-erasure.md): Patterns for tenant isolation, per-tenant collections, and safe data deletion in Weave.
- [Introduction](https://www.xraph.com/docs/weave.md): Composable RAG pipeline engine for Go.
- [Fabriq Vector Store](https://www.xraph.com/docs/weave/stores/fabriq.md): Back weave's VectorStore with the fabriq data fabric, so chunk embeddings live in the same store as the rest of your system.
- [In-Memory Store](https://www.xraph.com/docs/weave/stores/memory.md): In-memory MetadataStore and VectorStore for development, testing, and prototyping.
- [MongoDB Store](https://www.xraph.com/docs/weave/stores/mongo.md): Document-oriented MetadataStore using Grove ORM with mongodriver for MongoDB.
- [PostgreSQL Store](https://www.xraph.com/docs/weave/stores/postgres.md): Production MetadataStore backed by PostgreSQL using Grove ORM.
- [SQLite Store](https://www.xraph.com/docs/weave/stores/sqlite.md): Lightweight SQLite MetadataStore using Grove ORM with sqlitedriver.
- [HTTP API](https://www.xraph.com/docs/weave/subsystems/admin-api.md): The Weave REST API — 12 endpoints for collections, documents, retrieval, and search.
- [Embedder](https://www.xraph.com/docs/weave/subsystems/compliance.md): The Embedder interface and built-in implementations for generating vector embeddings.
- [Text Chunker](https://www.xraph.com/docs/weave/subsystems/erasure.md): The Chunker interface and built-in strategies for splitting documents into embeddable chunks.
- [Observability](https://www.xraph.com/docs/weave/subsystems/observability.md): Built-in metrics extension and tracing support for Weave lifecycle events.
- [Extension System](https://www.xraph.com/docs/weave/subsystems/plugins.md): Weave lifecycle hooks — reacting to ingestion, retrieval, collection, and reindex events.
- [Document Ingestion](https://www.xraph.com/docs/weave/subsystems/recording.md): How Weave ingests documents — the full load → chunk → embed → store pipeline.
- [Context Assembler](https://www.xraph.com/docs/weave/subsystems/retention.md): Building LLM-ready context strings from retrieved chunks with token budgeting and citations.
- [Document Loader](https://www.xraph.com/docs/weave/subsystems/sinks.md): The Loader interface and built-in format handlers for extracting text from documents.
- [Semantic Retrieval](https://www.xraph.com/docs/weave/subsystems/verification.md): How Weave retrieves relevant chunks — similarity, MMR, hybrid, and cross-collection search.