https://github.com/mh-anari/local-llms
Some useful notebooks for deploy open-source LLMs using Ollama and Langchain. Simple ChatBot, RAG and etc.
https://github.com/mh-anari/local-llms
chatbot langchain llm ollama rag-chatbot
Last synced: about 2 months ago
JSON representation
Some useful notebooks for deploy open-source LLMs using Ollama and Langchain. Simple ChatBot, RAG and etc.
- Host: GitHub
- URL: https://github.com/mh-anari/local-llms
- Owner: MH-Anari
- Created: 2025-04-06T10:45:52.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-07T22:00:28.000Z (about 1 year ago)
- Last Synced: 2025-04-07T22:32:19.221Z (about 1 year ago)
- Topics: chatbot, langchain, llm, ollama, rag-chatbot
- Language: Jupyter Notebook
- Homepage:
- Size: 19.5 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Run Gemma3:12B LLM locally with Ollama and Langchain
These Jupyter Notebooks allow you to easily run the Gemma3:12B LLM or any others locally using Ollama and Langchain. It's a convenient way to experiment with this powerful model without relying on external APIs.
**Note** : The contents of README file is also available in Lovely Persian via README_FA.md file.
## List of Projects
* **Simple ChatBot based on gemma3:12b (or any other)**
* **RAG ChatBot using a knowledge base with persian contexts for answering accuratly**
* **Maybe Continue...**
## Setup
It does not have any seprated setup. just run every notebook cells sequentially from the first.
## Usage
Feel free to use it for good purposes. these are for you without any api call for security of data and requests without any pay.
## Screenshot
## Potential Issues & Troubleshooting
* **Ollama Not Found:** Ensure Ollama is installed correctly and accessible in your system's PATH. Verify Ollama is running.
* **Download Errors:** If you encounter errors during the model download, check your internet connection and available disk space. Try clearing your Ollama cache: `ollama cache clean`.
* **Resource Constraints:** Running large language models requires significant computational resources (CPU, RAM, GPU). If you experience performance issues or errors, try using a smaller model of gemma3 or another.
* **Model Version Conflicts:** Make sure the model name used in the notebook (`gemma3:12b`) matches the version you have pulled with Ollama.
## Contributing
Feel free to fork this repository and submit pull requests for improvements or bug fixes.
## License
MIT License