Get-Things-Done-with-Prompt-Engineering-and-LangChain
LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Projects for using a private LLM (Llama 2) for chat with PDF files, tweets sentiment analysis.
- stars
- 1,252
- 30-day movement
- starts with the next reading
- Related entries
- 60
- Connections
- 1
This is a collection of LangChain and prompt engineering tutorials presented as Jupyter notebooks, covering loading and indexing data, prompt templates, CSV agents, and retrieval QA chains for querying custom data. It also includes project notebooks for chatting with PDF files using a private Llama 2 model and for tweet sentiment analysis.
Use it when you want runnable, notebook-based examples of LangChain workflows like retrieval QA, CSV agents, and prompt templates against your own data.
Use it to
- Work through LangChain tutorials on custom data queries
- Learn prompt template and retrieval QA patterns
- Build a Llama 2 chat with PDF project
- Explore CSV agent notebooks
- Study tweet sentiment analysis with LLMs
For Developers learning LangChain and prompt engineering with notebooks
- Role
- agent-framework
- Language
- Jupyter Notebook
- Licence
- Apache-2.0
- Forks
- 372
- Open issues
- 7
- Last push
- 2024-01-07