liaokongVFX/LangChain-Chinese-Getting-Started-Guide

Features

• LLM Application Frameworks - Serves as a comprehensive guide to building applications powered by large language models using the LangChain framework.
• Retrieval-Augmented Generation - Provides comprehensive tutorials for implementing retrieval augmented generation systems to ground model responses in external data.
• Autonomous Agents - Guides the creation of autonomous agents that integrate memory, tool usage, and decision-making to perform tasks.
• Chaining Pipelines - Sequences multiple language model calls and data processing steps into repeatable execution pipelines.
• RAG Implementations - Implements architectures that retrieve relevant documents from vector stores to augment LLM prompt context.
• RAG Tutorials - Delivers practical educational guides for implementing retrieval-augmented generation systems.
• Tool-Using Agents - Provides guides on creating agents that dynamically select and execute external tools based on user input.
• Natural Language to SQL - Maps natural language prompts to specific relational table definitions to generate executable database queries.
• Knowledge Base Construction - Walks through the full pipeline of parsing documents and generating embeddings for semantic retrieval.
• Local Knowledge Bases - Guides the construction of local systems for parsing and indexing documents for private information retrieval.
• LLM-Based SQL Generation - Translates natural language queries into executable SQL commands using language model schemas.
• Application Development Guides - Provides tutorials for building end-to-end applications that integrate LLMs with memory and logical chains.
• LLM Learning Resources - Offers a curated collection of Chinese-language tutorials and educational materials for learning LLM application development.
• Compositional Transformation Pipelines - Composes complex logic by chaining sequential data transformations and model calls into a single pipeline.
• Development Guides - Provides detailed walkthroughs for creating agents that dynamically select and execute external tools.
• Conversational Memory Systems - Manages and stores historical interaction data to provide context for ongoing AI conversations.
• Conversation Memory Stores - Implements conversational memory by storing and injecting interaction history to preserve context.
• Conversation State Persistence - Supports the persistence of conversation state and history across multiple interactions.
• Text Chunks - Provides methods for splitting documents into smaller segments to remain within token limits.
• Document Loaders - Includes guides on importing data from diverse formats like files and video transcripts.
• Vector Storage - Demonstrates how to use specialized storage engines to persist high-dimensional vectors for semantic search.
• Vector Memory Stores - Uses vector stores to index and retrieve relevant document chunks via semantic similarity search.
• Vector Storage - Converts text into numerical embeddings and stores them in databases for similarity lookups.
• Tutorials and Notebooks - Chinese language getting started guide.

Star history