OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Knowledgebase Rag LLM System

Knowledgebase Rag LLM System is a Python application for uploading TXT documents, storing their chunks in a persistent local Chroma vector database, and asking questions through a Streamlit chat interface. LangChain connects retrieval with prompts and model responses; the documented model setup uses Qwen through DashScope.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Knowledgebase Rag LLM System — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a self-hosted prototype for conversational search over TXT documents and can configure access to DashScope models.

Who it is for

  • Developers learning or adapting a retrieval-augmented generation workflow.
  • Teams prototyping chat over product, policy or other TXT documents.
  • Users exploring document chunking, vector retrieval and conversational follow-ups.

Documented uses

  • Upload TXT files and split their contents into chunks for a local Chroma knowledge base.
  • Ask questions answered using passages retrieved from the uploaded documents.
  • Continue a conversation with chat history and streamed model output.
  • Adjust chunking, retrieval and model settings in the configuration.
Before you choose

Requirements & limits

The documented setup requires a DashScope API key. The public repository displays an MIT license.

  • The documented upload workflow supports TXT files; other formats are described as extension ideas.
  • The vector database is persisted locally, but model calls use DashScope.
  • Upload and chat services need matching Chroma persistence-directory and collection-name settings.
  • The stack includes Python, Streamlit, LangChain, Chroma and Qwen.

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 two Streamlit apps

Install the application, configure DashScope access and start its upload and chat interfaces.

Before you start

  • Python 3.10 or later
  • A DashScope API key
  • The project repository and its requirements file

Steps

  1. Clone the repository and change into its directory.

  2. Install the dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. Set DASHSCOPE_API_KEY in the shell environment.

  4. In separate terminals, run streamlit run app_upload.py and streamlit run app_chat.py.

Expected outcome

The upload and question-answering Streamlit apps are launched; the README directs users to open localhost:8501 in a browser.

Guide limitations

  • The upload and chat apps must use the same Chroma persistence directory and collection name for retrieval to find uploaded documents.
  • The documented upload format is TXT.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

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
Knowledgebase Rag LLM SystemUpload TXT files and split their contents into chunks for a local Chroma knowledge base.Linux, macOS, Self-hosted, WebThe documented setup requires a DashScope API key. The public repository displays an MIT license.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
lhh737/KnowledgeBase-RAG-LLM-System · Official homepage title · retained in its source language
How we review sourcesSuggest a correction