LexiestLeszek/sova_ollama
Open source implementation of Sova - RAG-based Web search engine using power of LLMs. Using Langchain, Ollama, HuggingFace Embeddings and scraping google search results.
Sova helps you get direct, full-text answers to your web search queries instead of just a list of links. You provide a question or search term, and it uses powerful language models to scrape Google results and synthesize a comprehensive answer. Anyone who needs quick, summarized information from the web without sifting through multiple pages would find this useful.
No commits in the last 6 months.
Use this if you want to quickly find and synthesize information from multiple web sources into a single, direct answer, much like asking a knowledgeable assistant.
Not ideal if you need to browse specific websites, examine source documents in detail, or prefer to evaluate search results manually.
Stars
40
Forks
2
Language
HTML
License
MIT
Category
Last pushed
Feb 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/LexiestLeszek/sova_ollama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
run-llama/llama_index
LlamaIndex is the leading document agent and OCR platform
emarco177/documentation-helper
Reference implementation of a RAG-based documentation helper using LangChain, Pinecone, and Tavily..
janus-llm/janus-llm
Leveraging LLMs for modernization through intelligent chunking, iterative prompting and...
JetXu-LLM/llama-github
Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and...
Vasallo94/ObsidianRAG
RAG system to query your Obsidian notes using LangGraph and local LLMs (Ollama)