Welcome to the TalkPipe documentation! This directory contains guides, API references, and examples for using TalkPipe effectively.
New to TalkPipe? Start here for installation, basic concepts, and your first pipeline.
Create vector databases and run RAG servers in two commands: makevectordatabase and serverag.
Set default LLM and embedding providers via segment parameters, ~/.talkpipe.toml, or environment variables.
Pull multi-platform release images from GitHub Container Registry (ghcr.io), tags, and Docker/Podman usage.
Real-world usage examples and tutorials:
- Tutorial Overview
- Tutorial 1: Document Indexing - Basic TalkPipe concepts
- Tutorial 2: Search & RAG - Advanced search techniques
- Tutorial 3: Report Writing - Automated report generation
Complete documentation for all TalkPipe commands and components:
- chatterlang_serve - Run a script as an API endpoint with a customizable web interface
- ChatterLang Workbench - Interactive web interface for writing and testing scripts interactively
- ChatterLang Script Runner - Run a script from the command line
- Documentation Generator - Generate reference documentation for Segments and Sources
- Plugin Manager - Manage and inspect TalkPipe plugins
🏗️ Architecture
Deep technical documentation:
- Pipe API - Internal DSL and pipeline construction
- ChatterLang - External DSL language reference
- Extending TalkPipe - Creating custom components and plugins
- Configuration - Configuring variables for scripts
Glossary, repository conventions, shared parameter semantics (set_as, field, field_list, …), and standard ~/.talkpipe.toml keys—reference material for contributors and advanced users.
Found a gap or error? Documentation improvements are welcome! Please:
- Check existing issues for the topic
- Submit a pull request with your improvements
- Follow the existing documentation style and structure
- See Documentation Formatting for code block and example guidelines
For the main project overview and installation instructions, see the main README.