A series of notebooks containing implementations of various types of LLM Agents and related concepts.
01_langgraph_agents.ipynb
- Simple Bot: Integrating LLMs in Graphs for sending and handling different types of messages
- Chatbot With Memory: Create an agent with a Memory Layer
- ReAct Agent: Reasoning and Acting Agent to interact with Tools in LangGraph
- Document Drafter: A Fast agentic AI system that can speed up drafting documents, emails etc and save them afterwards.
- Agentic RAG: Combines the capabilities of traditional RAG with AI agents to enhance adaptability and accuracy in information retrieval and response generation.
02_agentic_memory.ipynb:
Create an agentic RAG with 4 kinds of memories:
- Working Memory - Current conversation and immediate context
- Episodic Memory - Historical experiences and their takeaways
- Semantic Memory - Knowledge context and factual grounding
- Procedural Memory - The "rules" and "skills" for interaction
03_llama3_web_research_agent.ipynb: An agent which can interact with an external web API to create report on user query.