https://github.com/navaneethelite/ollama_chat
Q&A application leveraging the Ollama language model (LLAMA 3.2:1b) to provide intelligent responses to user queries.
https://github.com/navaneethelite/ollama_chat
generative-ai langchain nlp ollama streamlit
Last synced: about 2 months ago
JSON representation
Q&A application leveraging the Ollama language model (LLAMA 3.2:1b) to provide intelligent responses to user queries.
- Host: GitHub
- URL: https://github.com/navaneethelite/ollama_chat
- Owner: NAVANEETHELITE
- Created: 2024-11-17T18:38:16.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-11-17T21:09:44.000Z (over 1 year ago)
- Last Synced: 2025-01-20T00:48:24.045Z (over 1 year ago)
- Topics: generative-ai, langchain, nlp, ollama, streamlit
- Language: Python
- Homepage:
- Size: 377 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# Q&A WITH LLAMA3
## DESCRIPTION
This Q&A application leverages the `Ollama` language model (LLAMA 3.2:1b) to provide intelligent responses to user queries.
## TOOLS AND MODELS
- **LANGCHAIN**
- **OllamaLLM**
- **STREAMLIT**
## MODEL INSTALLATION
Download and install [`Ollama`](https://ollama.com/download). Then pull the required model as follows:
```bash
ollama run llama3.2:1b
```
Ollama has to be running locally for this app to work.
## GENERATING API KEYS
Generate API key for Langsmith to get an interactive tracking of your requests to LLM via langchain [`here`](https://smith.langchain.com/settings).
Refer sample .env in project's root directory.
## INSTALLING REQUIREMENTS
```bash
pip install -r requirements.txt
```
## RUNNING THE APPLICATION
```bash
streamlit run app.py
```
#### Navigate to [`localhost`](http://localhost:8501) to interact with LLAMA3.
## HOME PAGE:
## LANGSMITH DASHBOARD:
