paper-qa

High accuracy RAG for answering questions from scientific documents with citations

Stars: 6197

Visit

PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and includes a process of embedding docs, queries, searching for top passages, creating summaries, using an LLM to re-score and select relevant summaries, putting summaries into prompt, and generating answers. The tool can be used to answer specific questions related to scientific research by leveraging citations and relevant passages from documents.

README:

PaperQA2

PaperQA2 is a package for doing high-accuracy retrieval augmented generation (RAG) on PDFs or text files, with a focus on the scientific literature. See our recent 2024 paper to see examples of PaperQA2's superhuman performance in scientific tasks like question answering, summarization, and contradiction detection.

Quickstart
- Example Output
What is PaperQA2
Installation
CLI Usage
- Bundled Settings
- Rate Limits
Library Usage
Where do I get papers?
- Zotero
- Paper Scraper
Callbacks
- Caching Embeddings
Customizing Prompts
- Pre and Post Prompts
FAQ
Citation

Quickstart

In this example we take a folder of research paper PDFs, magically get their metadata - including citation counts with a retraction check, then parse and cache PDFs into a full-text search index, and finally answer the user question with an LLM agent.

pip install paper-qa
cd my_papers
pqa ask 'How can carbon nanotubes be manufactured at a large scale?'

Example Output

Question: Has anyone designed neural networks that compute with proteins or DNA?

The claim that neural networks have been designed to compute with DNA is supported by multiple sources. The work by Qian, Winfree, and Bruck demonstrates the use of DNA strand displacement cascades to construct neural network components, such as artificial neurons and associative memories, using a DNA-based system (Qian2011Neural pages 1-2, Qian2011Neural pages 15-16, Qian2011Neural pages 54-56). This research includes the implementation of a 3-bit XOR gate and a four-neuron Hopfield associative memory, showcasing the potential of DNA for neural network computation. Additionally, the application of deep learning techniques to genomics, which involves computing with DNA sequences, is well-documented. Studies have applied convolutional neural networks (CNNs) to predict genomic features such as transcription factor binding and DNA accessibility (Eraslan2019Deep pages 4-5, Eraslan2019Deep pages 5-6). These models leverage DNA sequences as input data, effectively using neural networks to compute with DNA. While the provided excerpts do not explicitly mention protein-based neural network computation, they do highlight the use of neural networks in tasks related to protein sequences, such as predicting DNA-protein binding (Zeng2016Convolutional pages 1-2). However, the primary focus remains on DNA-based computation.

What is PaperQA2

PaperQA2 is engineered to be the best agentic RAG model for working with scientific papers. Here are some features:

A simple interface to get good answers with grounded responses containing in-text citations.
State-of-the-art implementation including document metadata-awareness in embeddings and LLM-based re-ranking and contextual summarization (RCS).
Support for agentic RAG, where a language agent can iteratively refine queries and answers.
Automatic redundant fetching of paper metadata, including citation and journal quality data from multiple providers.
A usable full-text search engine for a local repository of PDF/text files.
A robust interface for customization, with default support for all LiteLLM models.

By default, it uses OpenAI embeddings and models with a Numpy vector DB to embed and search documents. However, you can easily use other closed-source, open-source models or embeddings (see details below).

PaperQA2 depends on some awesome libraries/APIs that make our repo possible. Here are some in no particular order:

PaperQA2 vs PaperQA

We've been working on hard on fundamental upgrades for a while and mostly followed SemVer. meaning we've incremented the major version number on each breaking change. This brings us to the current major version number v5. So why call is the repo now called PaperQA2? We wanted to remark on the fact though that we've exceeded human performance on many important metrics. So we arbitrarily call version 5 and onward PaperQA2, and versions before it as PaperQA1 to denote the significant change in performance. We recognize that we are challenged at naming and counting at FutureHouse, so we reserve the right at any time to arbitrarily change the name to PaperCrow.

What's New in Version 5 (aka PaperQA2)?

Version 5 added:

A CLI pqa
Agentic workflows invoking tools for paper search, gathering evidence, and generating an answer
Removed much of the statefulness from the Docs object
A migration to LiteLLM for compatibility with many LLM providers as well as centralized rate limits and cost tracking
A bundled set of configurations (read here)) containing known-good hyperparameters

Note that Docs objects pickled from prior versions of PaperQA are incompatible with version 5, and will need to be rebuilt. Also, our minimum Python version was increased to Python 3.11.

PaperQA2 Algorithm

To understand PaperQA2, let's start with the pieces of the underlying algorithm. The default workflow of PaperQA2 is as follows:

Phase	PaperQA2 Actions
1. Paper Search	- Get candidate papers from LLM-generated keyword query
	- Chunk, embed, and add candidate papers to state
2. Gather Evidence	- Embed query into vector
	- Rank top k document chunks in current state
	- Create scored summary of each chunk in the context of the current query
	- Use LLM to re-score and select most relevant summaries
3. Generate Answer	- Put best summaries into prompt with context
	- Generate answer with prompt

The tools can be invoked in any order by a language agent. For example, an LLM agent might do a narrow and broad search, or using different phrasing for the gather evidence step from the generate answer step.

Installation

For a non-development setup, install PaperQA2 (aka version 5) from PyPI. Note version 5 requires Python 3.11+.

pip install paper-qa>=5

For development setup, please refer to the CONTRIBUTING.md file.

PaperQA2 uses an LLM to operate, so you'll need to either set an appropriate API key environment variable (i.e. export OPENAI_API_KEY=sk-...) or set up an open source LLM server (i.e. using llamafile. Any LiteLLM compatible model can be configured to use with PaperQA2.

If you need to index a large set of papers (100+), you will likely want an API key for both Crossref and Semantic Scholar, which will allow you to avoid hitting public rate limits using these metadata services. Those can be exported as CROSSREF_API_KEY and SEMANTIC_SCHOLAR_API_KEY variables.

CLI Usage

The fastest way to test PaperQA2 is via the CLI. First navigate to a directory with some papers and use the pqa cli:

$ pqa ask 'What manufacturing challenges are unique to bispecific antibodies?'

You will see PaperQA2 index your local PDF files, gathering the necessary metadata for each of them (using Crossref and Semantic Scholar), search over that index, then break the files into chunked evidence contexts, rank them, and ultimately generate an answer. The next time this directory is queried, your index will already be built (save for any differences detected, like new added papers), so it will skip the indexing and chunking steps.

All prior answers will be indexed and stored, you can view them by querying via the search subcommand, or access them yourself in your PQA_HOME directory, which defaults to ~/.pqa/.

$ pqa search -i 'answers' 'antibodies'

PaperQA2 is highly configurable, when running from the command line, pqa --help shows all options and short descriptions. For example to run with a higher temperature:

$ pqa --temperature 0.5 ask 'What manufacturing challenges are unique to bispecific antibodies?'

You can view all settings with pqa view. Another useful thing is to change to other templated settings - for example fast is a setting that answers more quickly and you can see it with pqa -s fast view

Maybe you have some new settings you want to save? You can do that with

pqa -s my_new_settings --temperature 0.5 --llm foo-bar-5 save

and then you can use it with

pqa -s my_new_settings ask 'What manufacturing challenges are unique to bispecific antibodies?'

If you run pqa with a command which requires a new indexing, say if you change the default chunk_size, a new index will automatically be created for you.

pqa --parsing.chunk_size 5000 ask 'What manufacturing challenges are unique to bispecific antibodies?'

You can also use pqa to do full-text search with use of LLMs view the search command. For example, let's save the index from a directory and give it a name:

pqa -i nanomaterials index

Now I can search for papers about thermoelectrics:

pqa -i nanomaterials search thermoelectrics

or I can use the normal ask

pqa -i nanomaterials ask 'Are there nm scale features in thermoelectric materials?'

Both the CLI and module have pre-configured settings based on prior performance and our publications, they can be invoked as follows:

pqa --settings <setting name> ask 'Are there nm scale features in thermoelectric materials?'

Bundled Settings

Inside paperqa/configs we bundle known useful settings:

Setting Name	Description
high_quality	Highly performant, relatively expensive (due to having `evidence_k` = 15) query using a `ToolSelector` agent.
fast	Setting to get answers cheaply and quickly.
wikicrow	Setting to emulate the Wikipedia article writing used in our WikiCrow publication.
contracrow	Setting to find contradictions in papers, your query should be a claim that needs to be flagged as a contradiction (or not).
debug	Setting useful solely for debugging, but not in any actual application beyond debugging.
tier1_limits	Settings that match OpenAI rate limits for each tier, you can use `tier<1-5>_limits` to specify the tier.

Rate Limits

If you are hitting rate limits, say with the OpenAI Tier 1 plan, you can add them into PaperQA2. For each OpenAI tier, a pre-built setting exists to limit usage.

pqa --settings 'tier1_limits' ask 'Are there nm scale features in thermoelectric materials?'

This will limit your system to use the tier1_limits, and slow down your queries to accommodate.

You can also specify them manually with any rate limit string that matches the specification in the limits module:

pqa --summary_llm_config '{"rate_limit": {"gpt-4o-2024-08-06": "30000 per 1 minute"}}' ask 'Are there nm scale features in thermoelectric materials?'

Or by adding into a Settings object, if calling imperatively:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(
        llm_config={"rate_limit": {"gpt-4o-2024-08-06": "30000 per 1 minute"}},
        summary_llm_config={"rate_limit": {"gpt-4o-2024-08-06": "30000 per 1 minute"}},
    ),
)

Library Usage

PaperQA2's full workflow can be accessed via Python directly:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(temperature=0.5, paper_directory="my_papers"),
)

Please see our installation docs for how to install the package from PyPI.

`ask` manually

The answer object has the following attributes: formatted_answer, answer (answer alone), question , and context (the summaries of passages found for answer). ask will use the SearchPapers tool, which will query a local index of files, you can specify this location via the Settings object:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(temperature=0.5, paper_directory="my_papers"),
)

ask is just a convenience wrapper around the real entrypoint, which can be accessed if you'd like to run concurrent asynchronous workloads:

from paperqa import Settings, agent_query, QueryRequest

answer = await agent_query(
    QueryRequest(
        query="What manufacturing challenges are unique to bispecific antibodies?",
        settings=Settings(temperature=0.5, paper_directory="my_papers"),
    )
)

The default agent will use an LLM based agent, but you can also specify a "fake" agent to use a hard coded call path of search -> gather evidence -> answer to reduce token usage.

Adding Documents Manually

If you prefer fine grained control, and you wish to add objects to the docs object yourself (rather than using the search tool), then the previously existing Docs object interface can be used:

from paperqa import Docs, Settings

# valid extensions include .pdf, .txt, and .html
doc_paths = ("myfile.pdf", "myotherfile.pdf")

docs = Docs()

for doc in doc_paths:
    docs.add(doc)

settings = Settings()
settings.llm = "claude-3-5-sonnet-20240620"
settings.answer.answer_max_sources = 3

answer = docs.query(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=settings,
)

print(answer.formatted_answer)

Async

PaperQA2 is written to be used asynchronously. The synchronous API is just a wrapper around the async. Here are the methods and their async equivalents:

Sync	Async
`Docs.add`	`Docs.aadd`
`Docs.add_file`	`Docs.aadd_file`
`Docs.add_url`	`Docs.aadd_url`
`Docs.get_evidence`	`Docs.aget_evidence`
`Docs.query`	`Docs.aquery`

The synchronous version just calls the async version in a loop. Most modern python environments support async natively (including Jupyter notebooks!). So you can do this in a Jupyter Notebook:

import asyncio
from paperqa import Docs


async def main() -> None:
    docs = Docs()
    # valid extensions include .pdf, .txt, and .html
    for doc in ("myfile.pdf", "myotherfile.pdf"):
        await docs.aadd(doc)

    answer = await docs.aquery(
        "What manufacturing challenges are unique to bispecific antibodies?"
    )
    print(answer.formatted_answer)


asyncio.run(main())

Choosing Model

By default, it uses OpenAI models with gpt-4o-2024-08-06 for both the re-ranking and summary step, the summary_llm setting, and for the answering step, the llm setting. You can adjust this easily:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(
        llm="gpt-4o-mini", summary_llm="gpt-4o-mini", paper_directory="my_papers"
    ),
)

You can use Anthropic or any other model supported by litellm:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(
        llm="claude-3-5-sonnet-20240620", summary_llm="claude-3-5-sonnet-20240620"
    ),
)

Locally Hosted

You can use llama.cpp to be the LLM. Note that you should be using relatively large models, because PaperQA2 requires following a lot of instructions. You won't get good performance with 7B models.

The easiest way to get set-up is to download a llama file and execute it with -cb -np 4 -a my-llm-model --embedding which will enable continuous batching and embeddings.

from paperqa import Settings, ask

local_llm_config = dict(
    model_list=[
        dict(
            model_name="my_llm_model",
            litellm_params=dict(
                model="my-llm-model",
                api_base="http://localhost:8080/v1",
                api_key="sk-no-key-required",
                temperature=0.1,
                frequency_penalty=1.5,
                max_tokens=512,
            ),
        )
    ]
)

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(
        llm="my-llm-model",
        llm_config=local_llm_config,
        summary_llm="my-llm-model",
        summary_llm_config=local_llm_config,
    ),
)

Models hosted with ollama are also supported. To run the example below make sure you have downloaded llama3.2 and mxbai-embed-large via ollama.

from paperqa import Settings, ask

local_llm_config = {
    "model_list": [
        {
            "model_name": "ollama/llama3.2",
            "litellm_params": {
                "model": "ollama/llama3.2",
                "api_base": "http://localhost:11434",
            },
        }
    ]
}

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(
        llm="ollama/llama3.2",
        llm_config=local_llm_config,
        summary_llm="ollama/llama3.2",
        summary_llm_config=local_llm_config,
        embedding="ollama/mxbai-embed-large",
    ),
)

Changing Embedding Model

PaperQA2 defaults to using OpenAI (text-embedding-3-small) embeddings, but has flexible options for both vector stores and embedding choices. The simplest way to change an embedding is via the embedding argument to the Settings object constructor:

from paperqa import Settings, ask

answer = ask(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=Settings(embedding="text-embedding-3-large"),
)

embedding accepts any embedding model name supported by litellm. PaperQA2 also supports an embedding input of "hybrid-<model_name>" i.e. "hybrid-text-embedding-3-small" to use a hybrid sparse keyword (based on a token modulo embedding) and dense vector embedding, where any litellm model can be used in the dense model name. "sparse" can be used to use a sparse keyword embedding only.

Embedding models are used to create PaperQA2's index of the full-text embedding vectors (texts_index argument). The embedding model can be specified as a setting when you are adding new papers to the Docs object:

from paperqa import Docs, Settings

docs = Docs()
for doc in ("myfile.pdf", "myotherfile.pdf"):
    docs.add(doc, settings=Settings(embedding="text-embedding-large-3"))

Note that PaperQA2 uses Numpy as a dense vector store. Its design of using a keyword search initially reduces the number of chunks needed for each answer to a relatively small number < 1k. Therefore, NumpyVectorStore is a good place to start, it's a simple in-memory store, without an index. However, if a larger-than-memory vector store is needed, we are currently lacking here.

The hybrid embeddings can be customized:

from paperqa import (
    Docs,
    HybridEmbeddingModel,
    SparseEmbeddingModel,
    LiteLLMEmbeddingModel,
)


model = HybridEmbeddingModel(
    models=[LiteLLMEmbeddingModel(), SparseEmbeddingModel(ndim=1024)]
)
docs = Docs()
for doc in ("myfile.pdf", "myotherfile.pdf"):
    docs.add(doc, embedding_model=model)

The sparse embedding (keyword) models default to having 256 dimensions, but this can be specified via the ndim argument.

Adjusting number of sources

You can adjust the numbers of sources (passages of text) to reduce token usage or add more context. k refers to the top k most relevant and diverse (may from different sources) passages. Each passage is sent to the LLM to summarize, or determine if it is irrelevant. After this step, a limit of max_sources is applied so that the final answer can fit into the LLM context window. Thus, k > max_sources and max_sources is the number of sources used in the final answer.

from paperqa import Settings

settings = Settings()
settings.answer.answer_max_sources = 3
settings.answer.k = 5

docs.query(
    "What manufacturing challenges are unique to bispecific antibodies?",
    settings=settings,
)

Using Code or HTML

You do not need to use papers -- you can use code or raw HTML. Note that this tool is focused on answering questions, so it won't do well at writing code. One note is that the tool cannot infer citations from code, so you will need to provide them yourself.

import glob
import os
from paperqa import Docs

source_files = glob.glob("**/*.js")

docs = Docs()
for f in source_files:
    # this assumes the file names are unique in code
    docs.add(f, citation="File " + os.path.name(f), docname=os.path.name(f))
answer = docs.query("Where is the search bar in the header defined?")
print(answer)

Using External DB/Vector DB and Caching

You may want to cache parsed texts and embeddings in an external database or file. You can then build a Docs object from those directly:

from paperqa import Docs, Doc, Text

docs = Docs()

for ... in my_docs:
    doc = Doc(docname=..., citation=..., dockey=..., citation=...)
    texts = [Text(text=..., name=..., doc=doc) for ... in my_texts]
    docs.add_texts(texts, doc)

Creating Index

Indexes will be placed in the home directory by default. This can be controlled via the PQA_HOME environment variable.

Indexes are made by reading files in the Settings.paper_directory. By default, we recursively read from subdirectories of the paper directory, unless disabled using Settings.index_recursively. The paper directory is not modified in any way, it's just read from.

Manifest Files

The indexing process attempts to infer paper metadata like title and DOI using LLM-powered text processing. You can avoid this point of uncertainty using a "manifest" file, which is a CSV containing three columns (order doesn't matter):

file_location: relative path to the paper's PDF within the index directory
doi: DOI of the paper
title: title of the paper

By providing this information, we ensure queries to metadata providers like Crossref are accurate.

Reusing Index

The local search indexes are built based on a hash of the current Settings object. So make sure you properly specify the paper_directory to your Settings object. In general, it's advisable to:

Pre-build an index given a folder of papers (can take several minutes)
Reuse the index to perform many queries

import os

from paperqa import Settings
from paperqa.agents.main import agent_query
from paperqa.agents.models import QueryRequest
from paperqa.agents.search import get_directory_index


async def amain(folder_of_papers: str | os.PathLike) -> None:
    settings = Settings(paper_directory=folder_of_papers)

    # 1. Build the index. Note an index name is autogenerated when unspecified
    built_index = await get_directory_index(settings=settings)
    print(settings.get_index_name())  # Display the autogenerated index name
    print(await built_index.index_files)  # Display the index contents

    # 2. Use the settings as many times as you want with ask
    answer_response_1 = await agent_query(
        query=QueryRequest(
            query="What is the best way to make a vaccine?", settings=settings
        )
    )
    answer_response_2 = await agent_query(
        query=QueryRequest(
            query="What manufacturing challenges are unique to bispecific antibodies?",
            settings=settings,
        )
    )

Running on LitQA v2

In paperqa/agents/task.py, you will find:

GradablePaperQAEnvironment: an environment that can grade answers given an evaluation function.
LitQAv2TaskDataset: a task dataset designed to pull LitQA v2 from Hugging Face, and create one GradablePaperQAEnvironment per question

Here is an example of how to use them:

import os

from aviary.env import TaskDataset
from ldp.agent import SimpleAgent
from ldp.alg.callbacks import MeanMetricsCallback
from ldp.alg.runners import Evaluator, EvaluatorConfig

from paperqa import QueryRequest, Settings
from paperqa.agents.task import TASK_DATASET_NAME


async def evaluate(folder_of_litqa_v2_papers: str | os.PathLike) -> None:
    base_query = QueryRequest(
        settings=Settings(paper_directory=folder_of_litqa_v2_papers)
    )
    dataset = TaskDataset.from_name(TASK_DATASET_NAME, base_query=base_query)
    metrics_callback = MeanMetricsCallback(eval_dataset=dataset)

    evaluator = Evaluator(
        config=EvaluatorConfig(batch_size=3),
        agent=SimpleAgent(),
        dataset=dataset,
        callbacks=[metrics_callback],
    )
    await evaluator.evaluate()

    print(metrics_callback.eval_means)

Using Clients Directly

One of the most powerful features of PaperQA2 is its ability to combine data from multiple metadata sources. For example, Unpaywall can provide open access status/direct links to PDFs, Crossref can provide bibtex, and Semantic Scholar can provide citation licenses. Here's a short demo of how to do this:

from paperqa.clients import DocMetadataClient, ALL_CLIENTS

client = DocMetadataClient(clients=ALL_CLIENTS)
details = await client.query(title="Augmenting language models with chemistry tools")

print(details.formatted_citation)
# Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D. White, and Philippe Schwaller.
#  Augmenting large language models with chemistry tools. Nature Machine Intelligence,
# 6:525-535, May 2024. URL: https://doi.org/10.1038/s42256-024-00832-8,
# doi:10.1038/s42256-024-00832-8.
# This article has 243 citations and is from a domain leading peer-reviewed journal.

print(details.citation_count)
# 243

print(details.license)
# cc-by

print(details.pdf_url)
# https://www.nature.com/articles/s42256-024-00832-8.pdf

the client.query is meant to check for exact matches of title. It's a bit robust (like to casing, missing a word). There are duplicates for titles though - so you can also add authors to disambiguate. Or you can provide a doi directly client.query(doi="10.1038/s42256-024-00832-8").

If you're doing this at a large scale, you may not want to use ALL_CLIENTS (just omit the argument) and you can specify which specific fields you want to speed up queries. For example:

details = await client.query(
    title="Augmenting large language models with chemistry tools",
    authors=["Andres M. Bran", "Sam Cox"],
    fields=["title", "doi"],
)

will return much faster than the first query and we'll be certain the authors match.

Where do I get papers?

Well that's a really good question! It's probably best to just download PDFs of papers you think will help answer your question and start from there.

Zotero

It's been a while since we've tested this - so let us know if it runs into issues!

If you use Zotero to organize your personal bibliography, you can use the paperqa.contrib.ZoteroDB to query papers from your library, which relies on pyzotero.

Install pyzotero via the zotero extra for this feature:

pip install paperqa[zotero]

First, note that PaperQA2 parses the PDFs of papers to store in the database, so all relevant papers should have PDFs stored inside your database. You can get Zotero to automatically do this by highlighting the references you wish to retrieve, right clicking, and selecting "Find Available PDFs". You can also manually drag-and-drop PDFs onto each reference.

To download papers, you need to get an API key for your account.

Get your library ID, and set it as the environment variable ZOTERO_USER_ID.
- For personal libraries, this ID is given here at the part "Your userID for use in API calls is XXXXXX".
- For group libraries, go to your group page https://www.zotero.org/groups/groupname, and hover over the settings link. The ID is the integer after /groups/. (h/t pyzotero!)
Create a new API key here and set it as the environment variable ZOTERO_API_KEY.
- The key will need read access to the library.

With this, we can download papers from our library and add them to PaperQA2:

from paperqa import Docs
from paperqa.contrib import ZoteroDB

docs = Docs()
zotero = ZoteroDB(library_type="user")  # "group" if group library

for item in zotero.iterate(limit=20):
    if item.num_pages > 30:
        continue  # skip long papers
    docs.add(item.pdf, docname=item.key)

which will download the first 20 papers in your Zotero database and add them to the Docs object.

We can also do specific queries of our Zotero library and iterate over the results:

for item in zotero.iterate(
    q="large language models",
    qmode="everything",
    sort="date",
    direction="desc",
    limit=100,
):
    print("Adding", item.title)
    docs.add(item.pdf, docname=item.key)

You can read more about the search syntax by typing zotero.iterate? in IPython.

Paper Scraper

If you want to search for papers outside of your own collection, I've found an unrelated project called paper-scraper that looks like it might help. But beware, this project looks like it uses some scraping tools that may violate publisher's rights or be in a gray area of legality.

from paperqa import Docs

keyword_search = "bispecific antibody manufacture"
papers = paperscraper.search_papers(keyword_search)
docs = Docs()
for path, data in papers.items():
    try:
        docs.add(path)
    except ValueError as e:
        # sometimes this happens if PDFs aren't downloaded or readable
        print("Could not read", path, e)
answer = docs.query(
    "What manufacturing challenges are unique to bispecific antibodies?"
)
print(answer)

Callbacks

To execute a function on each chunk of LLM completions, you need to provide a function that can be executed on each chunk. For example, to get a typewriter view of the completions, you can do:

def typewriter(chunk: str) -> None:
    print(chunk, end="")


docs = Docs()

# add some docs...

docs.query(
    "What manufacturing challenges are unique to bispecific antibodies?",
    callbacks=[typewriter],
)

Caching Embeddings

In general, embeddings are cached when you pickle a Docs regardless of what vector store you use. So as long as you save your underlying Docs object, you should be able to avoid re-embedding your documents.

Customizing Prompts

You can customize any of the prompts using settings.

from paperqa import Docs, Settings

my_qa_prompt = (
    "Answer the question '{question}'\n"
    "Use the context below if helpful. "
    "You can cite the context using the key like (Example2012). "
    "If there is insufficient context, write a poem "
    "about how you cannot answer.\n\n"
    "Context: {context}"
)

docs = Docs()
settings = Settings()
settings.prompts.qa = my_qa_prompt
docs.query("Are covid-19 vaccines effective?", settings=settings)

Pre and Post Prompts

Following the syntax above, you can also include prompts that are executed after the query and before the query. For example, you can use this to critique the answer.

FAQ

How come I get different results than your papers?

Internally at FutureHouse, we have a slightly different set of tools. We're trying to get some of them, like citation traversal, into this repo. However, we have APIs and licenses to access research papers that we cannot share openly. Similarly, in our research papers' results we do not start with the known relevant PDFs. Our agent has to identify them using keyword search over all papers, rather than just a subset. We're gradually aligning these two versions of PaperQA, but until there is an open-source way to freely access papers (even just open source papers) you will need to provide PDFs yourself.

How is this different from LlamaIndex or LangChain?

LangChain and LlamaIndex are both frameworks for working with LLM applications, with abstractions made for agentic workflows and retrieval augmented generation.

Over time, the PaperQA team over time chose to become framework-agnostic, instead outsourcing LLM drivers to LiteLLM and no framework besides Pydantic for its tools. PaperQA focuses on scientific papers and their metadata.

PaperQA can be reimplemented using either LlamaIndex or LangChain. For example, our GatherEvidence tool can be reimplemented as a retriever with an LLM-based re-ranking and contextual summary. There is similar work with the tree response method in LlamaIndex.

Can I save or load?

The Docs class can be pickled and unpickled. This is useful if you want to save the embeddings of the documents and then load them later.

import pickle

# save
with open("my_docs.pkl", "wb") as f:
    pickle.dump(docs, f)

# load
with open("my_docs.pkl", "rb") as f:
    docs = pickle.load(f)

Citation

Please read and cite the following papers if you use this software:

@article{skarlinski2024language,
  title={Language agents achieve superhuman synthesis of scientific knowledge},
  author={
    Michael D. Skarlinski and
    Sam Cox and
    Jon M. Laurent and
    James D. Braza and
    Michaela Hinks and
    Michael J. Hammerling and
    Manvitha Ponnapati and
    Samuel G. Rodriques and
    Andrew D. White},
  year={2024},
  journal={arXiv preprent arXiv:2409.13740},
  url={https://doi.org/10.48550/arXiv.2409.13740}
}


@article{lala2023paperqa,
  title={PaperQA: Retrieval-Augmented Generative Agent for Scientific Research},
  author={L{\'a}la, Jakub and O'Donoghue, Odhran and Shtedritski, Aleksandar and Cox, Sam and Rodriques, Samuel G and White, Andrew D},
  journal={arXiv preprint arXiv:2312.07559},
  year={2023}
}

For Tasks:

Click tags to check more tools for each tasks

answer questions search for relevant passages generate summaries re-score answers embed documents

For Jobs:

research assistant data scientist academic writer scientific researcher knowledge engineer

Alternative AI tools for paper-qa

Similar Open Source Tools

paper-qa

github

: 6.2k

paper-qa

PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and follows a process of embedding docs and queries, searching for top passages, creating summaries, scoring and selecting relevant summaries, putting summaries into prompt, and generating answers. Users can customize prompts and use various models for embeddings and LLMs. The tool can be used asynchronously and supports adding documents from paths, files, or URLs.

github

: 3.6k

py-vectara-agentic

The `vectara-agentic` Python library is designed for developing powerful AI assistants using Vectara and Agentic-RAG. It supports various agent types, includes pre-built tools for domains like finance and legal, and enables easy creation of custom AI assistants and agents. The library provides tools for summarizing text, rephrasing text, legal tasks like summarizing legal text and critiquing as a judge, financial tasks like analyzing balance sheets and income statements, and database tools for inspecting and querying databases. It also supports observability via LlamaIndex and Arize Phoenix integration.

github

: 64

elmer

Elmer is a user-friendly wrapper over common APIs for calling llm’s, with support for streaming and easy registration and calling of R functions. Users can interact with Elmer in various ways, such as interactive chat console, interactive method call, programmatic chat, and streaming results. Elmer also supports async usage for running multiple chat sessions concurrently, useful for Shiny applications. The tool calling feature allows users to define external tools that Elmer can request to execute, enhancing the capabilities of the chat model.

github

: 70

web-llm

WebLLM is a modular and customizable javascript package that directly brings language model chats directly onto web browsers with hardware acceleration. Everything runs inside the browser with no server support and is accelerated with WebGPU. WebLLM is fully compatible with OpenAI API. That is, you can use the same OpenAI API on any open source models locally, with functionalities including json-mode, function-calling, streaming, etc. We can bring a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration.

github

: 13.1k

BentoVLLM

BentoVLLM is an example project demonstrating how to serve and deploy open-source Large Language Models using vLLM, a high-throughput and memory-efficient inference engine. It provides a basis for advanced code customization, such as custom models, inference logic, or vLLM options. The project allows for simple LLM hosting with OpenAI compatible endpoints without the need to write any code. Users can interact with the server using Swagger UI or other methods, and the service can be deployed to BentoCloud for better management and scalability. Additionally, the repository includes integration examples for different LLM models and tools.

github

: 62

curate-gpt

CurateGPT is a prototype web application and framework for performing general purpose AI-guided curation and curation-related operations over collections of objects. It allows users to load JSON, YAML, or CSV data, build vector database indexes for ontologies, and interact with various data sources like GitHub, Google Drives, Google Sheets, and more. The tool supports ontology curation, knowledge base querying, term autocompletion, and all-by-all comparisons for objects in a collection.

github

: 56

WindowsAgentArena

Windows Agent Arena (WAA) is a scalable Windows AI agent platform designed for testing and benchmarking multi-modal, desktop AI agents. It provides researchers and developers with a reproducible and realistic Windows OS environment for AI research, enabling testing of agentic AI workflows across various tasks. WAA supports deploying agents at scale using Azure ML cloud infrastructure, allowing parallel running of multiple agents and delivering quick benchmark results for hundreds of tasks in minutes.

github

: 147

ell

ell is a lightweight, functional prompt engineering framework that treats prompts as programs rather than strings. It provides tools for prompt versioning, monitoring, and visualization, as well as support for multimodal inputs and outputs. The framework aims to simplify the process of prompt engineering for language models.

github

: 4.8k

leptonai

A Pythonic framework to simplify AI service building. The LeptonAI Python library allows you to build an AI service from Python code with ease. Key features include a Pythonic abstraction Photon, simple abstractions to launch models like those on HuggingFace, prebuilt examples for common models, AI tailored batteries, a client to automatically call your service like native Python functions, and Pythonic configuration specs to be readily shipped in a cloud environment.

github

: 2.5k

HuggingFaceGuidedTourForMac

HuggingFaceGuidedTourForMac is a guided tour on how to install optimized pytorch and optionally Apple's new MLX, JAX, and TensorFlow on Apple Silicon Macs. The repository provides steps to install homebrew, pytorch with MPS support, MLX, JAX, TensorFlow, and Jupyter lab. It also includes instructions on running large language models using HuggingFace transformers. The repository aims to help users set up their Macs for deep learning experiments with optimized performance.

github

: 79

unstructured

The `unstructured` library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. The use cases of `unstructured` revolve around streamlining and optimizing the data processing workflow for LLMs. `unstructured` modular functions and connectors form a cohesive system that simplifies data ingestion and pre-processing, making it adaptable to different platforms and efficient in transforming unstructured data into structured outputs.

github

: 8.8k

ScandEval

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

github

: 69

marvin

Marvin is a lightweight AI toolkit for building natural language interfaces that are reliable, scalable, and easy to trust. Each of Marvin's tools is simple and self-documenting, using AI to solve common but complex challenges like entity extraction, classification, and generating synthetic data. Each tool is independent and incrementally adoptable, so you can use them on their own or in combination with any other library. Marvin is also multi-modal, supporting both image and audio generation as well using images as inputs for extraction and classification. Marvin is for developers who care more about _using_ AI than _building_ AI, and we are focused on creating an exceptional developer experience. Marvin users should feel empowered to bring tightly-scoped "AI magic" into any traditional software project with just a few extra lines of code. Marvin aims to merge the best practices for building dependable, observable software with the best practices for building with generative AI into a single, easy-to-use library. It's a serious tool, but we hope you have fun with it. Marvin is open-source, free to use, and made with 💙 by the team at Prefect.

github

: 5.2k

fasttrackml

FastTrackML is an experiment tracking server focused on speed and scalability, fully compatible with MLFlow. It provides a user-friendly interface to track and visualize your machine learning experiments, making it easy to compare different models and identify the best performing ones. FastTrackML is open source and can be easily installed and run with pip or Docker. It is also compatible with the MLFlow Python package, making it easy to integrate with your existing MLFlow workflows.

github

: 97

llm-verified-with-monte-carlo-tree-search

This prototype synthesizes verified code with an LLM using Monte Carlo Tree Search (MCTS). It explores the space of possible generation of a verified program and checks at every step that it's on the right track by calling the verifier. This prototype uses Dafny, Coq, Lean, Scala, or Rust. By using this technique, weaker models that might not even know the generated language all that well can compete with stronger models.

github

: 218

For similar tasks

LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github

: 1.5k

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

onnxruntime-genai

ONNX Runtime Generative AI is a library that provides the generative AI loop for ONNX models, including inference with ONNX Runtime, logits processing, search and sampling, and KV cache management. Users can call a high level `generate()` method, or run each iteration of the model in a loop. It supports greedy/beam search and TopP, TopK sampling to generate token sequences, has built in logits processing like repetition penalties, and allows for easy custom scoring.

github

: 442

jupyter-ai

Jupyter AI connects generative AI with Jupyter notebooks. It provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in JupyterLab and the Jupyter Notebook. Specifically, Jupyter AI offers: * An `%%ai` magic that turns the Jupyter notebook into a reproducible generative AI playground. This works anywhere the IPython kernel runs (JupyterLab, Jupyter Notebook, Google Colab, Kaggle, VSCode, etc.). * A native chat UI in JupyterLab that enables you to work with generative AI as a conversational assistant. * Support for a wide range of generative model providers, including AI21, Anthropic, AWS, Cohere, Gemini, Hugging Face, NVIDIA, and OpenAI. * Local model support through GPT4All, enabling use of generative AI models on consumer grade machines with ease and privacy.

github

: 3.2k

khoj

Khoj is an open-source, personal AI assistant that extends your capabilities by creating always-available AI agents. You can share your notes and documents to extend your digital brain, and your AI agents have access to the internet, allowing you to incorporate real-time information. Khoj is accessible on Desktop, Emacs, Obsidian, Web, and Whatsapp, and you can share PDF, markdown, org-mode, notion files, and GitHub repositories. You'll get fast, accurate semantic search on top of your docs, and your agents can create deeply personal images and understand your speech. Khoj is self-hostable and always will be.

github

: 12.8k

langchain_dart

LangChain.dart is a Dart port of the popular LangChain Python framework created by Harrison Chase. LangChain provides a set of ready-to-use components for working with language models and a standard interface for chaining them together to formulate more advanced use cases (e.g. chatbots, Q&A with RAG, agents, summarization, extraction, etc.). The components can be grouped into a few core modules: * **Model I/O:** LangChain offers a unified API for interacting with various LLM providers (e.g. OpenAI, Google, Mistral, Ollama, etc.), allowing developers to switch between them with ease. Additionally, it provides tools for managing model inputs (prompt templates and example selectors) and parsing the resulting model outputs (output parsers). * **Retrieval:** assists in loading user data (via document loaders), transforming it (with text splitters), extracting its meaning (using embedding models), storing (in vector stores) and retrieving it (through retrievers) so that it can be used to ground the model's responses (i.e. Retrieval-Augmented Generation or RAG). * **Agents:** "bots" that leverage LLMs to make informed decisions about which available tools (such as web search, calculators, database lookup, etc.) to use to accomplish the designated task. The different components can be composed together using the LangChain Expression Language (LCEL).

github

: 408

danswer

Danswer is an open-source Gen-AI Chat and Unified Search tool that connects to your company's docs, apps, and people. It provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for configuring Personas (AI Assistants) and their Prompts. Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc. By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already supported?" or "Where's the pull request for feature Y?"

github

: 10.5k

infinity

Infinity is an AI-native database designed for LLM applications, providing incredibly fast full-text and vector search capabilities. It supports a wide range of data types, including vectors, full-text, and structured data, and offers a fused search feature that combines multiple embeddings and full text. Infinity is easy to use, with an intuitive Python API and a single-binary architecture that simplifies deployment. It achieves high performance, with 0.1 milliseconds query latency on million-scale vector datasets and up to 15K QPS.

github

: 2.5k

For similar jobs

SLR-FC

This repository provides a comprehensive collection of AI tools and resources to enhance literature reviews. It includes a curated list of AI tools for various tasks, such as identifying research gaps, discovering relevant papers, visualizing paper content, and summarizing text. Additionally, the repository offers materials on generative AI, effective prompts, copywriting, image creation, and showcases of AI capabilities. By leveraging these tools and resources, researchers can streamline their literature review process, gain deeper insights from scholarly literature, and improve the quality of their research outputs.

github

: 110

paper-ai

Paper-ai is a tool that helps you write papers using artificial intelligence. It provides features such as AI writing assistance, reference searching, and editing and formatting tools. With Paper-ai, you can quickly and easily create high-quality papers.

github

: 664

paper-qa

PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and follows a process of embedding docs and queries, searching for top passages, creating summaries, scoring and selecting relevant summaries, putting summaries into prompt, and generating answers. Users can customize prompts and use various models for embeddings and LLMs. The tool can be used asynchronously and supports adding documents from paths, files, or URLs.

github

: 3.6k

ChatData

ChatData is a robust chat-with-documents application designed to extract information and provide answers by querying the MyScale free knowledge base or uploaded documents. It leverages the Retrieval Augmented Generation (RAG) framework, millions of Wikipedia pages, and arXiv papers. Features include self-querying retriever, VectorSQL, session management, and building a personalized knowledge base. Users can effortlessly navigate vast data, explore academic papers, and research documents. ChatData empowers researchers, students, and knowledge enthusiasts to unlock the true potential of information retrieval.

github

: 135

noScribe

noScribe is an AI-based software designed for automated audio transcription, specifically tailored for transcribing interviews for qualitative social research or journalistic purposes. It is a free and open-source tool that runs locally on the user's computer, ensuring data privacy. The software can differentiate between speakers and supports transcription in 99 languages. It includes a user-friendly editor for reviewing and correcting transcripts. Developed by Kai Dröge, a PhD in sociology with a background in computer science, noScribe aims to streamline the transcription process and enhance the efficiency of qualitative analysis.

github

: 398

AIStudyAssistant

AI Study Assistant is an app designed to enhance learning experience and boost academic performance. It serves as a personal tutor, lecture summarizer, writer, and question generator powered by Google PaLM 2. Features include interacting with an AI chatbot, summarizing lectures, generating essays, and creating practice questions. The app is built using 100% Kotlin, Jetpack Compose, Clean Architecture, and MVVM design pattern, with technologies like Ktor, Room DB, Hilt, and Kotlin coroutines. AI Study Assistant aims to provide comprehensive AI-powered assistance for students in various academic tasks.

github

: 69

data-to-paper

Data-to-paper is an AI-driven framework designed to guide users through the process of conducting end-to-end scientific research, starting from raw data to the creation of comprehensive and human-verifiable research papers. The framework leverages a combination of LLM and rule-based agents to assist in tasks such as hypothesis generation, literature search, data analysis, result interpretation, and paper writing. It aims to accelerate research while maintaining key scientific values like transparency, traceability, and verifiability. The framework is field-agnostic, supports both open-goal and fixed-goal research, creates data-chained manuscripts, involves human-in-the-loop interaction, and allows for transparent replay of the research process.

github

: 453

k2

K2 (GeoLLaMA) is a large language model for geoscience, trained on geoscience literature and fine-tuned with knowledge-intensive instruction data. It outperforms baseline models on objective and subjective tasks. The repository provides K2 weights, core data of GeoSignal, GeoBench benchmark, and code for further pretraining and instruction tuning. The model is available on Hugging Face for use. The project aims to create larger and more powerful geoscience language models in the future.

github

: 153

paper-qa

README:

PaperQA2

Quickstart

Example Output

What is PaperQA2

PaperQA2 vs PaperQA

What's New in Version 5 (aka PaperQA2)?

PaperQA2 Algorithm

Installation

CLI Usage

Bundled Settings

Rate Limits

Library Usage

ask manually

Adding Documents Manually

Async

Choosing Model

Locally Hosted

Changing Embedding Model

Adjusting number of sources

Using Code or HTML

Using External DB/Vector DB and Caching

Creating Index

Manifest Files

Reusing Index

Running on LitQA v2

Using Clients Directly

Where do I get papers?

Zotero

Paper Scraper

Callbacks

Caching Embeddings

Customizing Prompts

Pre and Post Prompts

FAQ

How come I get different results than your papers?

How is this different from LlamaIndex or LangChain?

Can I save or load?

Citation

For Tasks:

For Jobs:

Alternative AI tools for paper-qa

Similar Open Source Tools

paper-qa

paper-qa

py-vectara-agentic

elmer

web-llm

BentoVLLM

curate-gpt

WindowsAgentArena

ell

leptonai

HuggingFaceGuidedTourForMac

unstructured

ScandEval

marvin

fasttrackml

llm-verified-with-monte-carlo-tree-search

For similar tasks

LLMStack

ai-guide

onnxruntime-genai

jupyter-ai

khoj

langchain_dart

danswer

infinity

For similar jobs

SLR-FC

paper-ai

paper-qa

ChatData

noScribe

AIStudyAssistant

data-to-paper

k2

`ask` manually