OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Local RAG Researcher with DeepSeek R1 & LangGraph

A self-hosted Python research agent that uses LangGraph to coordinate retrieval-augmented research with DeepSeek R1 served by Ollama. It searches a local Chroma database, evaluates retrieved documents, can expand research through Tavily web search, and passes findings to a writer agent for structured reports in a Streamlit interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Local RAG Researcher with DeepSeek R1 & LangGraph — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to explore a self-hosted research workflow over a local Chroma document collection, with optional web search and configurable report structures.

Who it is for

  • Developers prototyping research agents over internal or locally stored documents.
  • Researchers who want a local-model workflow for gathering and summarizing information.
  • Builders exploring LangGraph, retrieval-augmented generation, Ollama and DeepSeek R1 together.

Documented uses

  • Turn a user instruction into research questions and retrieve relevant local documents.
  • Assess retrieved material and summarize key findings.
  • Expand a local-document search with Tavily when more sources are needed.
  • Format findings as a report using a selected structure.
Before you choose

Requirements & limits

The documented application is run from the Python repository on a self-hosted setup. The README lists Python 3.9 or later and Ollama as prerequisites; it describes a Tavily API key as optional for web search.

  • The default model path is local: DeepSeek R1 runs through Ollama.
  • Retrieval uses a local Chroma database; web search is a separate Tavily-backed expansion.
  • The report writer follows predefined structures, and additional structures can be added in report_structures.
  • Using an external LLM provider requires code changes in assistant/graph.py and an OpenRouter API key.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and launch the local research app

Prepare the repository, install the specified local model, and start its Streamlit interface.

Before you start

  • Python 3.9 or later
  • Ollama
  • Git and the repository's requirements.txt dependencies
  • A Tavily API key only if using its web-search feature

Steps

  1. Clone the repository and change into its directory.

  2. Create and activate a Python virtual environment, then install dependencies with pip install -r requirements.txt.

  3. Create a root .env file; add TAVILY_API_KEY if web search is needed.

  4. Install Ollama, pull deepseek-r1:7b, and launch the interface with streamlit run app.py.

Expected outcome

The documented setup sequence launches the Streamlit interface with DeepSeek R1 served through Ollama.

Guide limitations

  • The README does not specify hardware requirements or guarantee compatibility across environments.
  • Web search depends on Tavily and its API key; the project describes that key as optional.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Local RAG Researcher with DeepSeek R1 & LangGraphTurn a user instruction into research questions and retrieve relevant local documents.Self-hostedThe documented application is run from the Python repository on a self-hosted setup. The README lists Python 3.9 or later and Ollama as prerequisites; it describes a Tavily API key as optional for web search.
NaviLawAsk a legal question in the context of multiple uploaded PDF documents.WebThe source repository is public and identifies an MIT license. The repository links to a Streamlit web application and documents a self-hosted setup.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
kaymen99/local-rag-researcher-deepseek · Official homepage title · retained in its source language
How we review sourcesSuggest a correction