Welcome to Apsara AI, an innovative project powered by Streamlit, Groq, and Ollama! 🚀
Apsara AI features a cutting-edge Chatbot and RAG (Retrieval Augmentation Generation) system designed to enhance conversational experiences and streamline information retrieval from various documents.
-
Chatbot: Engage in real-time conversations with Apsara using advanced conversational capabilities powered by Groq and Ollama.
-
RAG (Retrieval Augmentation Generation): Extract information from PDFs, Docs, or websites effortlessly with Apsara's RAG system.
- home.py: Contains the home page (used this for running the interface)
- chatbot.py: Contains the code for the Chatbot component of Apsara AI.
- rag.py: Contains the code for the RAG (Retrieval Augmentation Generation) component of Apsara AI.
-
Download Ollama:
- Visit Ollama's official website to download the Ollama software.
-
Install Ollama:
- Follow the instructions provided on the Ollama website to install the software on your system.
-
Pull Local Embeddings:
- To pull the local embeddings, run the following command in your terminal:
ollama pull nomic-embed-text
- To pull the local embeddings, run the following command in your terminal:
-
Pull Local LLM (Optional):
- If you want to use a local LLM, run the following command in your terminal:
ollama pull openchat
- If you want to use a local LLM, run the following command in your terminal:
-
Verify Installation:
- After installation, you can verify that Ollama and the required components are installed correctly by running:
ollama --version
- After installation, you can verify that Ollama and the required components are installed correctly by running:
-
Clone the repository:
git clone https://github.com/your-username/apsara-ai.git
-
Install requirements.txt:
- Install requirements.txt file by following command
pip install -r requirements.txt- Run the Streamlit App:
streamlit run home.py