Building a Body of Knowledge using Pinecone Serverless, Langchain and OpenAI for Wardley Mapping

See the following blog series on how to use and how this code works.

Building a Wardley Mapping Body of Knowledge using YouTube, Pinecone, Langchain, and OpenAI:

Part 1: A Step-By-Step Guide for data collection and extraction

Part 2: Transcribing the Audio Files

Part 3: Creating the vector database

Part 4: Querying the vector database using OpenAI/ChatGPT

Part 5: Query the Wardley Mapping PDF book using ChatGPT by adding an additional namepace to the vector database

Part 6: Extending the Wardley Mapping Body of Knowledge with Wardley Map blog posts

Part 7: Extending the Wardley Mapping Body of Knowledge with Twitter

Part 8: Extending the Wardley Mapping Body of Knowledge with the Research 2022 Wardley Maps from GitHub

Part 9: Analysing all the Wardley Mapping Text

Part 10: How to create a tweet summarising a Wardley Mapping blog post

Part 11: Try various different LangChian receivers to query data

Part 12: Collect Google Data Mesh Podcasts for GPT4 analysis

Part 13: Google Data Mesh Podcasts, speach to text

Part 14: Upsert Data Mesh Podcasts data into FAISS or Pinecone

Part 15: Query Data Mesh Podcasts

Part 16: Extending the Wardley Mapping Body of Knowledge - Part 16: Using Pinecone Serverless for Vector Database

Part 17: Extending the Wardley Mapping Body of Knowledge - Part 17: Extracting Wardley Mapping Terms and Concepts from Web Pages and Large Documents

Part 18: TBA - With Development Team

Part 19: TBA - With Development Team

Part 20: TBA - With Development Team

Part 21: TBA - With Development Team

Author

Contributing

Feel free to submit issues and pull requests to improve the application. For major changes, please open an issue first to discuss what you would like to change.