manupaiva/langchain-chatbot-memory

• .env: Contains environment variables, such as API keys.
• .env.example: Example of the .env file.
• .python-version: Specifies the Python version used in the project.
• memory.ipynb: Jupyter Notebook containing the main code for the project.
• requirements.txt: Lists the dependencies required for the project.

Setup

1. Clone the repository:

   git clone <repository-url>
   cd <repository-directory>

2. Create a virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows use `.venv\Scripts\activate`

3. Install the dependencies:

   pip install -r requirements.txt

4. Set up environment variables:

   • Copy .env.example to .env:

     cp .env.example .env

   • Fill in the required values in the .env file.

Usage

1. Run the Jupyter Notebook:

   jupyter notebook memory.ipynb

2. Execute the cells in memory.ipynb to see the Conversational RAG Chain in action.

Key Components

• Session History Retrieval:

  messages = conversational_rag_chain.get_session_history("abc123").messages

• Message Formatting:

  for i, message in enumerate(messages):
      if isinstance(message, HumanMessage):
          print(f"Human: {message.content}")
      elif isinstance(message, AIMessage):
          print(f"AI: {message.content}")
      print()  # Adds a blank line between each pair of messages

• Chain Creation:

  history_aware_retriever = create_history_aware_retriever(llm, retriever, contextualize_q_prompt)
  question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
  rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)

• Invoke Chain:

  conversational_rag_chain.invoke(
      {"input": "Where the people surf in the beginnings?"},
      config={
          "configurable": {"session_id": "abc123"}
      },
  )["answer"]

Dependencies

• langchain
• langchain-community
• langchainhub
• langchain-chroma
• beautifulsoup4
• python-dotenv
• langchain-openai

License

This project is licensed under the MIT License.