datawhalechina/llm-cookbook

Features

• LLM Application Development - Serves as a comprehensive guide for building software that integrates model logic with user interfaces.
• Application Development Guides - Serves as a comprehensive application development guide for building software powered by large language models.
• Agentic Tool Orchestration - Provides technical walkthroughs for orchestrating tools and APIs to build autonomous AI agents.
• AI Agent Development - Guides the development of autonomous entities that execute functions and use external tools.
• Autonomous Agent Orchestration - Provides frameworks for the orchestration and lifecycle management of autonomous agents.
• Context Augmentation Tools - Provides implementations for retrieving external data from knowledge bases to augment model context.
• Retrieval Augmented Generation - Implements systems that ground language model responses in external data via vector storage.
• LLM Application Frameworks - Provides methodologies and patterns for building functional applications powered by large language models.
• Prompt Engineering - Teaches the practice of designing and refining inputs to optimize model performance for specific tasks.
• Prompt Engineering Frameworks - Offers a framework of techniques and templates for optimizing input instructions to guide model reasoning.
• Prompt Engineering Guides - Provides a framework and guides for optimizing precise input instructions for LLM tasks.
• RAG Frameworks - Provides a development framework for building retrieval-augmented generation applications.
• RAG Tutorials - Provides comprehensive educational guides for implementing retrieval augmented generation using vector databases and semantic search.
• Vector Databases - Implements semantic search using embedding models and vector databases for context injection.
• AI Observability and Evaluation - Provides systematic tools for tracking and debugging AI outputs to ensure quality and consistency.
• LLM Application Orchestration - Implements tools for chaining model calls and coordinating complex agentic workflows.
• Generative AI Interfaces - Includes tutorials for deploying interactive user frontends for generative AI applications.
• Language Model Fine-Tuning - Tutorials on adapting open-source models to private datasets using specialized training techniques.
• Model Fine-Tuning - Includes technical walkthroughs for adapting pre-trained model weights using private datasets for domain-specific tasks.
• Model API Integrations - Demonstrates how to interface with large language models via standardized REST endpoints.
• Prompt-Based Logic Engines - Instructs on constructing structured input templates to guide multi-step reasoning and data transformation.
• Supervised Fine-Tuning - Offers guidance on adapting pre-trained model weights using curated private datasets for specialized tasks.
• Prompt Optimization - Offers methods for refining prompts to implement common functions like summarization and transformation.
• Learning and Reference - LLM introductory tutorial for developers.

Star history