This is a simple library of all the data loaders / readers that have been created by the community. The goal is to make it extremely easy to connect large language models to a large variety of knowledge sources. These are general-purpose utilities that are meant to be used in LlamaIndex (e.g. when building a index) and LangChain (e.g. when building different tools an agent can use). For example, there are loaders to parse Google Docs, SQL Databases, PDF files, PowerPoints, Notion, Slack, Obsidian, and many more. Note that because different loaders produce the same types of Documents, you can easily use them together in the same index.
Check out our website here: https://llamahub.ai/.
These general-purpose loaders are designed to be used as a way to load data into LlamaIndex and/or subsequently used as a Tool in a LangChain Agent. You can use them with download_loader from LlamaIndex in a single line of code! For example, see the code snippets below using the Google Docs Loader.
from llama_index import GPTSimpleVectorIndex, download_loader
GoogleDocsReader = download_loader('GoogleDocsReader')
gdoc_ids = ['1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec']
loader = GoogleDocsReader()
documents = loader.load_data(document_ids=gdoc_ids)
index = GPTSimpleVectorIndex(documents)
index.query('Where did the author go to school?')Note: Make sure you change the description of the Tool to match your use-case.
from llama_index import GPTSimpleVectorIndex, download_loader
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
# load documents
GoogleDocsReader = download_loader('GoogleDocsReader')
gdoc_ids = ['1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec']
loader = GoogleDocsReader()
documents = loader.load_data(document_ids=gdoc_ids)
langchain_documents = [d.to_langchain_format() for d in documents]
# initialize sample QA chain
llm = OpenAI(temperature=0)
qa_chain = load_qa_chain(llm)
question="<query here>"
answer = qa_chain.run(input_documents=langchain_documents, question=question)Adding a loader simply requires forking this repo and making a Pull Request. The Loader Hub website will update automatically. However, please keep in the mind the following guidelines when making your PR.
In loader_hub, create a new directory for your new loader. It can be nested within another, but name it something unique because the name of the directory will become the identifier for your loader (e.g. google_docs). Inside your new directory, create a __init__.py file, which can be empty, a base.py file which will contain your loader implementation, and, if needed, a requirements.txt file to list the package dependencies of your loader. Those packages will automatically be installed when your loader is used, so no need to worry about that anymore!
If you'd like, you can create the new directory and files by running the following script in the loader_hub directory. Just remember to put your dependencies into a requirements.txt file.
./add_loader.sh [NAME_OF_NEW_DIRECTORY]
Inside your new directory, create a README.md that mirrors that of the existing ones. It should have a summary of what your loader does, its inputs, and how its used in the context of LlamaIndex and LangChain.
Finally, add your loader to the loader_hub/library.json file so that it may be used by others. As is exemplified by the current file, add in the class name of your loader, along with its id, author, etc. This file is referenced by the Loader Hub website and the download function within LlamaIndex.
Create a PR against the main branch. We typically review the PR within a day. To help expedite the process, it may be helpful to provide screenshots (either in the PR or in the README directly) showing your data loader in action!
python3.9 -m venv .venv
source .venv/bin/activate
pip3 install -r test_requirements.txt
python3 -m pytest tests There is an argument called loader_hub_url in download_loader that defaults to the main branch of this repo. You can set it to your branch or fork to test your new loader.
If you have a data loader PR, by default let's try to create it against LlamaHub! We will make exceptions in certain cases (for instance, if we think the data loader should be core to the LlamaIndex repo).
For all other PR's relevant to LlamaIndex, let's create it directly against the LlamaIndex repo.
Feel free to hop into the community Discord or tag the official Twitter account!