curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain
Practical LLM Apps in Python, One Notebook at a Time
Teaches developers how to build and deploy real-world LLM apps using LangChain through hands-on Jupyter notebooks.
Not currently ranked — collecting fresh signals.
star history
What it does
This repository is a curated stack of Jupyter notebooks that teaches Python developers how to build practical applications with large language models using LangChain. The material starts with fundamentals—loading and indexing data, prompt templates, chains, memory, and agents—then advances to projects like chatting with PDFs, crypto tweet sentiment analysis, fine-tuning Llama 2 and Falcon 7B with QLoRA, and deploying to HuggingFace Inference Endpoints or RunPod. Most tutorials include an “Open in Colab” badge, and the project roster spans from local chatbots to single-GPU production deployment.
The interesting bit
The repo refuses to pick a side in the open-vs-closed model debate; it treats GPT-4, Llama 2, Falcon, and GPT4All as tools in the same belt. That flexibility turns what could be a scattered tutorial dump into a coherent curriculum that runs from first chain to production inference.
Key highlights
- Covers both OpenAI APIs and local open-source models (Llama 2, Falcon 7B, StableVicuna, GPT4All)
- Includes end-to-end deployment projects for HuggingFace Inference Endpoints and RunPod
- Provides executable Colab notebooks and paired YouTube walkthroughs
- Addresses advanced topics like QLoRA fine-tuning and AutoGen multi-agent systems
- Progresses from basic loaders and chains to support chatbots and deployed inference
Verdict
Best suited for Python developers who know the basics of LLMs and want a structured, project-based path toward deployment. Not for those seeking a reusable software library or a pure theory reference.
Frequently asked
- What is curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain?
- Teaches developers how to build and deploy real-world LLM apps using LangChain through hands-on Jupyter notebooks.
- Is Get-Things-Done-with-Prompt-Engineering-and-LangChain open source?
- Yes — curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain is open source, released under the Apache-2.0 license.
- What language is Get-Things-Done-with-Prompt-Engineering-and-LangChain written in?
- curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain is primarily written in Jupyter Notebook.
- How popular is Get-Things-Done-with-Prompt-Engineering-and-LangChain?
- curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain has 1.2k stars on GitHub.
- Where can I find Get-Things-Done-with-Prompt-Engineering-and-LangChain?
- curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain is on GitHub at https://github.com/curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain.