#1111th of 12 in RAG and search

ai-starter-kit

SambaNova Python kits for document RAG, search assistant, function calling

Stars
250
License
Apache-2.0
Last commit
Oct 2026
Last release
Oct 2025
Language
Jupyter Notebook

Overview

Nine Python kits, each with its own README: document text extraction, enterprise and multimodal knowledge retrieval with Streamlit demos, a RAG evaluation kit, a web search assistant, a financial assistant using function calling and scraping, a function-calling module, benchmarking and chat templates. Everything calls SambaNova models through SAMBANOVA_API_KEY. For teams on SambaCloud or SambaStack who want working retrieval code.

Who it is for: Teams on SambaNova who want working retrieval code

Strengths

  • Knowledge retriever and search assistant kits include runnable Streamlit demos
  • Makefile base environment installs Python, Poetry, Tesseract and Poppler; Docker option
  • RAG evaluation kit included

Weaknesses

  • SambaNova endpoints only; swapping providers means editing each kit
  • README states the code is as-is and not production-ready
  • Mixed notebooks and apps; no single app to fork
  • Heavy setup: pyenv, Poetry, a parsing service and OCR system packages

What it needs

  • Jupyter Notebook, sambanova, langchain
  • Needs sambanova-api-key, tesseract, poppler
  • Docker

Also in RAG and search

See all 12
Also in RAG and search
RankProjectScore
1azure-search-openai-demoAzure RAG chat reference on AI Search and Azure OpenAI7.8k stars, MIT56 out of 100
2rag-postgres-openai-pythonRAG over Postgres table rows with hybrid search and SQL filters505 stars, MIT51 out of 100
3llm-appPathway RAG pipeline templates that re-index live data sources Live demo ↗ (opens in a new tab)58.8k stars, MIT48 out of 100
#4chat-langchainLangChain docs assistant as a Managed Deep Agent with Next.js UI6.5k stars, MIT45 out of 100
#5chat-with-your-data-solution-acceleratorAzure RAG chat app that answers from your documents with citations1.2k stars, MIT44 out of 100