LangChain_Basics_with_Ollama

Here is a consolidated list of the tasks i performed using the LangChain framework

1. LLM Access: LangChain provides a unified interface to access and use various Large Language Models (LLMs) from different providers.
2. Prompt Templates: LangChain allows to create reusable and dynamic prompts by inserting variables into a predefined template.
3. Chains: Langchain allows to create Chains which link together multiple components (like LLMs, other chains, or tools) in a defined sequence to automate complex workflows.
4. ChatHistory(Memory): LangChain helps a chatbot remember past conversational turns, allowing for a more continuous and context-aware dialogue.
5. Embeddings: Langchain provides a standardized interface for embeddings which is used for similarity search
6. Vector Stores: Langchain provides a standardized interface for Vector stores to efficiently store and query numerical embeddings, enabling fast semantic search
7. RAG: LangChain allows to implement RAG to improve the accuracy of its responses
8. Agent: LangChain allows to create Agents that use an LLM or reasoning and have access to various tools to perform complex, multi-step tasks.
9. MCP: We use fastMCP framework to create MCP Server that exposes a specific set of tools and data. Then, we use a LangChain agent to act as a client that connects to MCP server, giving the agent's LLM access to those tools.