Graphrag cookbook httpx timeout error

Hey @Swarn22! I'm here to assist you with any issues you're experiencing with the Graphrag cookbook. I can help you with bug fixes, answer your questions, and guide you on becoming a contributor. Let me know how I can help!

Yes, there are known issues related to HTTPX timeout errors in the GraphRAG cookbook. Specifically, a user reported experiencing timeout errors when trying to build indexes, which is taking a long time and eventually timing out. This issue is related to loading a CSV and treating each row as a document ^[1].

To handle or configure timeouts for HTTPX requests, you can use the request_timeout field to set the timeout for HTTP requests. Here is an example of how to configure it:

request_timeout: float = Field(
    default=DEFAULT_REQUEST_TIMEOUT,
    description="The timeout for making http request to llamafile API server",
)

with httpx.Client(timeout=Timeout(self.request_timeout)) as client:
    response = client.post(
        url=f"{self.base_url}/embedding",
        headers={"Content-Type": "application/json"},
        json=request_body,
    )
    response.encoding = "utf-8"
    response.raise_for_status()
    return response.json()["embedding"]

async with httpx.AsyncClient(timeout=Timeout(self.request_timeout)) as client:
    response = await client.post(
        url=f"{self.base_url}/embedding",
        headers={"Content-Type": "application/json"},
        json=request_body,
    )
    response.encoding = "utf-8"
    response.raise_for_status()
    return response.json()["embedding"]

These snippets show how to configure and handle timeouts for HTTPX requests ^[2].

To continue talking to Dosu, mention @dosu.

run-llama / llama_index

Graphrag cookbook httpx timeout error #15740

Question Validation

Question