This loader takes in IDs of Google Docs and parses their text into Documents. You can extract a Google Doc's ID directly from its URL. For example, the ID of https://docs.google.com/document/d/1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec/edit is 1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec.

As a prerequisite, you will need to register with Google and generate a credentials.json file in the directory where you run this loader. See here for instructions.

Usage

To use this loader, you simply need to pass in an array of Google Doc IDs.

from gpt_index import download_loader

GoogleDocsReader = download_loader('GoogleDocsReader')

gdoc_ids = ['1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec']
loader = GoogleDocsReader()
documents = loader.load_data(document_ids=gdoc_ids)

Examples

This loader is designed to be used as a way to load data into GPT Index and/or subsequently used as a Tool in a LangChain Agent.

GPT Index

from gpt_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?')

LangChain

Note: Make sure you change the description of the Tool to match your use-case.

from gpt_index import GPTSimpleVectorIndex, download_loader
from langchain.agents import initialize_agent, Tool
from langchain.llms import OpenAI
from langchain.chains.conversation.memory import ConversationBufferMemory

GoogleDocsReader = download_loader('GoogleDocsReader')

gdoc_ids = ['1wf-y2pd9C878Oh-FmLH7Q_BQkljdm6TQal-c1pUfrec']
loader = GoogleDocsReader()
documents = loader.load_data(document_ids=gdoc_ids)
index = GPTSimpleVectorIndex(documents)

tools = [
    Tool(
        name="Google Doc Index",
        func=lambda q: index.query(q),
        description=f"Useful when you want answer questions about the Google Documents.",
    ),
]
llm = OpenAI(temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history")
agent_chain = initialize_agent(
    tools, llm, agent="zero-shot-react-description", memory=memory
)

output = agent_chain.run(input="Where did the author go to school?")