A developer building a LangGraph agent that reads shared Google Docs needs clean document content before reasoning or summarising. Google Docs shared via “anyone with the link” serve a full Drive UI with comment sidebars, suggestion overlays, and navigation chrome that obscures the document body, and the Drive API requires OAuth and project setup before a single document can be read. EnConvert Distill accepts the shared Google Doc URL, applies a schema the agent defines, and returns structured fields in one synchronous call. The agent gets structured document content ready for downstream reasoning with no Drive API credentials.
How to Summarise Google Docs with LangGraph
Google Docs summarisation in LangGraph: EnConvert Distill returns schema-defined fields from up to 50 shared URLs in one synchronous call, no Drive API setup
Get API keyExample
python
import os
import requests
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.graph import START, MessagesState, StateGraph
from langgraph.prebuilt import ToolNode, tools_condition
# ChatOpenAI reads OPENAI_API_KEY from the environment
GOOGLE_DOC_URL = os.environ["GOOGLE_DOC_URL"] # a Google Doc shared as "Anyone with the link can view"
BASE_URL = "https://api.enconvert.com/v2"
headers = {
"X-API-Key": os.environ["ENCONVERT_API_KEY"],
"Content-Type": "application/json",
}
# The fields the agent receives. The response keys match these names exactly.
DOC_SCHEMA = {
"title": "The document title",
"summary": "A three sentence summary of what the document covers",
"key_points": "The main points or decisions in the document, as a list",
"author": "The document owner or author, if the page shows one",
"last_edited": "The date the document was last edited, if the page shows one",
}
@tool
def summarise_google_docs(urls: list[str]) -> str:
"""Reads shared Google Docs and returns structured fields for each document:
title, summary, key points, author, and last edited date."""
if len(urls) > 50:
return "Too many URLs. Distill accepts at most 50 per call."
# One synchronous call: no job_id, no polling, no download step
response = requests.post(
f"{BASE_URL}/distill",
headers=headers,
json={"urls": urls, "schema": DOC_SCHEMA},
timeout=300,
)
# Distill runs on paid plans only, and the free tier returns 402
if response.status_code == 402:
return "Distill requires a paid plan."
response.raise_for_status()
documents = []
for result in response.json()["results"]:
# Failed pages come back as rows with a failed status, not as errors
if result["status"] != "completed":
documents.append(f"Source: {result['url']}\nCould not be read ({result['status']}).")
continue
# A render_quality below 0.5 may mean a login wall or challenge page
render_quality = result.get("render_quality", 1.0)
if render_quality < 0.5:
documents.append(
f"Source: {result['url']}\nLow render quality ({render_quality}), skipped."
)
continue
data = result["data"] # keys match DOC_SCHEMA exactly
points = data["key_points"]
documents.append(
f"Source: {result['url']}\n"
f"Title: {data['title']}\n"
f"Author: {data['author']}\n"
f"Last edited: {data['last_edited']}\n"
f"Key points: {'; '.join(points) if isinstance(points, list) else points}\n"
f"Summary: {data['summary']}"
)
return "\n\n---\n\n".join(documents)
tools = [summarise_google_docs]
llm = ChatOpenAI(model="gpt-4.1").bind_tools(tools)
def agent_node(state: MessagesState):
return {"messages": [llm.invoke(state["messages"])]}
# The graph: the agent calls the tool when it needs a document, then answers
builder = StateGraph(MessagesState)
builder.add_node("agent", agent_node)
builder.add_node("tools", ToolNode(tools))
builder.add_edge(START, "agent")
builder.add_conditional_edges("agent", tools_condition) # routes to "tools" or ends
builder.add_edge("tools", "agent")
graph = builder.compile()
result = graph.invoke(
{
"messages": [
(
"system",
"You summarise shared Google Docs. Use summarise_google_docs to read the "
"documents you need, answer only from what it returns, and cite the document "
"URL for every statement.",
),
(
"user",
f"Read {GOOGLE_DOC_URL} "
"and summarise it, listing its key points.",
),
]
}
)
print(result["messages"][-1].content)
What you get back
Distill returns the schema-defined fields inline as structured JSON in the data object, with no polling, no job_id, and no signed URL to fetch. The render_quality score lets the agent detect a login wall or challenge page before reasoning over incomplete content. The Google Drive API requires OAuth 2.0 credentials, a GCP project, and a separate export call to retrieve document content, while Distill requires only the shared link and an API key.