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

E Library Agent

E Library Agent is a self-hosted AI assistant that ingests user-provided files into a Qdrant vector collection, retrieves relevant passages to answer library questions, and uses Linkup-backed web search to find books or papers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

E Library Agent — 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 create a self-hosted, searchable document library and have a separate web-search route for finding books or papers.

Who it is for

  • People building a searchable library from their own files.
  • Researchers seeking a workflow that combines document retrieval with web searches for books or papers.

Documented uses

  • Progressively ingest files into a searchable collection.
  • Retrieve relevant context from that collection to answer questions.
  • Search the internet for books or papers.
Before you choose

Requirements & limits

The documented setup runs locally at http://localhost:8000 and requires Docker, Docker Compose, an OpenAI API key and a Linkup API key. The software is licensed under MIT.

  • Document ingestion uses text extraction and NeuralChunker-based chunking through ingest-anything.
  • OpenAI text-embedding-3-small creates 1,536-dimensional embeddings stored in Qdrant.
  • Library retrieval and web search use separate agent workflows, with relevance evaluation before context is used in a response.
  • The setup requires credentials for both OpenAI and Linkup.

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 E Library Agent with Docker Compose

Configure the required credentials and start the Qdrant and application containers.

Before you start

  • Docker and Docker Compose
  • An OpenAI API key
  • A Linkup API key

Steps

  1. Clone the repository and enter its directory.

  2. Add the openai_api_key and linkup_api_key variables to .env.example, then rename the file to .env.

  3. Start Qdrant with docker compose up qdrant -d.

  4. Start the application with docker compose up app -d.

Expected outcome

The README says the application will run at http://localhost:8000 after setup.

Guide limitations

  • The documented setup time can be as long as 15 minutes on the first run, depending on connection and hardware.
  • This guide covers setup and launch, not uploading files or querying the application.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
AstraBert/e-library-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction