Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. PaperQA2
Developer Tools
PaperQA2 icon

PaperQA2

by FutureHouse

PaperQA2 is a Python package for retrieval augmented question answering over scientific papers and other documents. It gives answers with in-text citations and can run as an agent that refines its own searches.

Agent·Free

View on GitHub(opens in a new tab)

About PaperQA2

Key features of PaperQA2

  • Question answering with in-text citations
  • Agentic mode that refines queries and answers
  • Re-ranking and contextual summarization
  • Automatic paper metadata, citation counts and retraction checks
  • Full-text search over a local folder of PDFs and text files
  • Reads PDFs, text, Office documents and code
  • Any LiteLLM provider, with local model options
  • Command line tool and Python library

Who PaperQA2 is for

  • Researchers reviewing scientific literature
  • Developers building document question answering
  • Teams that need cited answers from their own papers

How to use PaperQA2

  1. 1

    Step 1: Install the package with pip install paper-qa.

  2. 2

    Step 2: Put the PDFs you want to query in a folder.

  3. 3

    Step 3: Run pqa ask with your question from that folder.

  4. 4

    Step 4: Read the cited answer, or use the library to add and query documents in code.

  5. 5

    Step 5: Change the LLM, embedding model or settings to fit your setup.

PaperQA2 FAQ

What file types can it read?

PDFs, text files, Microsoft Office documents and source code files.

Which language models can I use?

It supports all LiteLLM providers, and it can also run with locally hosted models and local embedding models.

How does the agent differ from a basic search?

The agent can search for papers, gather evidence and write an answer, and it can refine queries and answers over several steps.

Where do paper details come from?

It fetches metadata such as citation counts and journal quality from multiple providers, and it relies on services such as Semantic Scholar and Crossref.

Details

Pricing
Free
Type
Agent
Platforms
  • API
  • CLI
Categories
Developer ToolsResearch
Added
Sep 16, 2026
FutureHouse iconPublisherFutureHouse

Built from public sources

We put this page together from PaperQA2’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with PaperQA2.

Work at PaperQA2? Claim the listing to manage it yourself.

Something wrong here?

More from FutureHouse

View publisher
FutureHouse Platform iconFutureHouse PlatformFutureHouse · FreemiumScientific-agent platform for literature search, deep research, evidence synthesis, novelty checking, and chemistry and biology research workflowsAI · FreemiumAviary iconAviaryFutureHouse · FreeAviary is an open-source gymnasium from FutureHouse for defining custom language-agent reinforcement learning environments. It ships with environments for math, general knowledge, biological sequences and scientific literature search.Developer Tools · Free

Related tools

See more
Aemon iconAemonAemon · Contact for pricingAemon is an AI R&D engineer: you give it a problem and an eval, and it runs research loops in your codebase to find validated improvements. Engagements start with an eval setup.Developer Tools · Contact for pricingOpen Deep Research iconOpen Deep ResearchHugging Face · FreeOpen Deep Research is Hugging Face's open-source reproduction of a web-browsing research agent, built in a 24-hour effort. It uses an agent framework that writes its actions as code.Developer Tools · FreeCaCajalCajal Technologies · Contact for pricingAI mathematician platform using formal verification to discover and validate solutions in applied scientific and technical domainsDeveloper Tools · Contact for pricing