Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ssk-14/wizsearch
Your intelligent ally for effortless information retrieval and seamless browsing across documents and the web.
https://github.com/ssk-14/wizsearch
gpt-4o langfuse llm multimodal ollama openai perplexity qdrant rag replicate streamlit tavily
Last synced: 11 days ago
JSON representation
Your intelligent ally for effortless information retrieval and seamless browsing across documents and the web.
- Host: GitHub
- URL: https://github.com/ssk-14/wizsearch
- Owner: SSK-14
- License: mit
- Created: 2024-05-14T16:07:49.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-08-26T13:57:41.000Z (3 months ago)
- Last Synced: 2024-08-26T16:25:06.222Z (3 months ago)
- Topics: gpt-4o, langfuse, llm, multimodal, ollama, openai, perplexity, qdrant, rag, replicate, streamlit, tavily
- Language: Python
- Homepage: https://wizsearch.streamlit.app/
- Size: 13.4 MB
- Stars: 18
- Watchers: 2
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ✨ WizSearch
Your intelligent ally for effortless data retrieval across documents and seamless browsing the web.
## Demo 🎬
1. Get your API key [groq](https://console.groq.com/keys)
2. Checkout https://wizsearch.streamlit.app/
[Quick start with Ollama in local 🦙✨](./docs/OLLAMA.md)
https://github.com/user-attachments/assets/fa4fae96-6e78-474d-9d90-2e1d64833008
## How we built it 🛠️
We built Wiz Search using the following components:
- **LLM/VLM:** Open source models like llama3.1, mistral, LLaVA, etc are supported by platforms such as [Ollama](https://ollama.ai/) and [Groq](https://console.groq.com/docs/models). Closed source models like gpt-4o, gpt-4 supported by [OpenAI](https://platform.openai.com/docs/models) and [Azure OpenAI](https://azure.microsoft.com/en-in/products/ai-services/openai-service) for natural language understanding and generation.
- **Embeddings:** `jina-embeddings-v2-base-en` and `BM25` using [fastembed](https://github.com/qdrant/fastembed) to enhance search relevance.
- **Intelligent Search:** [Tavily](https://tavily.com/) for advanced search capabilities.
- **Vector Databases:** [Qdrant](https://qdrant.tech/) for efficient data storage and retrieval.
- **Observability:** [Langfuse](https://www.langfuse.com/) for monitoring and observability.
- **UI:** [Streamlit](https://streamlit.io/) for creating an interactive and user-friendly interface.
## Run The Application ⚙️
1. Clone the repo
```
git clone https://github.com/SSK-14/WizSearch.git
```
2. Installation and setup
```
bash setup.sh
```
3. Running
```
streamlit run app.py
```
## Contributing 🤝
Contributions to this project are welcome! If you find any issues or have suggestions for improvement, please open an issue or submit a pull request on the project's GitHub repository.
## License 📝
This project is licensed under the [MIT License](https://github.com/SSK-14/WizSearch/blob/main/LICENSE). Feel free to use, modify, and distribute the code as per the terms of the license.