ChatGPT with your own Data

1. RAG
2. Azure/azure-openai-samples
   • Quick Start
   • Fundamentals
   • Use Cases
   • Sample Solutions
   • Serverless SQL GPT
3. openai/openai-cookbook
   • examples
     • Question_answering_using_embeddings.ipynb
     • Embedding_long_inputs.ipynb
     • Semantic_text_search_using_embeddings.ipynb
4. style
   • github
   • colab
   • demo
5. toggle
6. Tokenizer
7. Prompt Engineering
   • Prompt-Engineering-Guide: github
   • promptingguide.ai

     Revolutionize your Enterprise Data with ChatGPT: Next-gen Apps w/ Azure OpenAI and Cognitive Search

Chatting with your own data

1. One approach to have ChatGPT generate responses based on your own data is simple: inject this information into the prompt.
2. This presents a new challenge though: these models have a limit on the “context length” they support (the current ChatGPT model can take up to 4000 tokens in a prompt), and even if they didn’t have those limits, it wouldn’t be practical to inject GBs worth of data into a text prompt in each interaction.

##