🦜⛓️‍💥 Simplified LangChain for Go

Pipe (Chain) uses Input, Model and Output to make the interaction with the model easier.

Concepts

Core

Input -> Model -> Output

Agents

LLM -> Agent Tools -> Agent Agent -> Executor (Iterator)

(Agents: Static Validator/Limits/Logger)

Core

• Input: Chat messages and prompt
• Models: Ollama and OpenAI
• Parser: String, Json, Markdown, Symbol-Seperator and Map
• Pipe: Simple pipe to easily use input, models and output.
• Embedder: For vector embeddings
• Evaluator: Whitelist or Blacklist output before parsing (Soon in pipe and agent available)

Agents

• Basic Agent using the ReAct Pattern
• Static Tools use (Probably add input instruction)
• Agent Executer
• Limits and Logging of Agents and Executor
• Static Agent validator

RAG Retrival Argument Generation

• Similarity Search (Jaccard and Cosine)
• Vector Database (Qdrant)

Extensions

• Tools (.txt, pdf, ...)

Examples

• Core (Input, Model, Output, Pipe, Embedder)
• Temperature and time Agents
• RAG: Simple RAG with Jaccard
• Vectorstore: Qdrant