run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Agent functions never complete when using the python SDK inside Google Cloud functions. #477

New Issue
Open
opened 2026-02-16 00:17:57 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @Antigaprime on GitHub (May 16, 2025).

Describe the bug
Methods for creating, deleting, fetching, etc, agents for use with LlamaExtract never complete when working with the python SDK in Google Cloud functions.

Client:

  • Python SDK Library
    • Python 3.13 (Ubuntu 22)

Additional context
Any operations that involve agents never complete. Running the exact same code locally works fine.

Sample code:

requirements.py
functions-framework==3.*
llama-cloud-services==0.6.22
main.py
import functions_framework
from llama_cloud_services import LlamaExtract


extractor = LlamaExtract(
    verbose=True,
)


def get_or_create_agent(name: str, schema: dict):
    try:
        agent = extractor.create_agent(name=name, data_schema=schema)
    except Exception as e:
        print(f"Error creating agent (might already exist): {e}")
        agent = extractor.get_agent(name=name)
        agent.data_schema = schema
    return agent


@functions_framework.http
def main(request):
    """HTTP Cloud Function.
    Args:
        request (flask.Request): The request object.
        <https://flask.palletsprojects.com/en/1.1.x/api/#incoming-request-data>
    Returns:
        The response text, or any set of values that can be turned into a
        Response object using `make_response`
        <https://flask.palletsprojects.com/en/1.1.x/api/#flask.make_response>.
    """
    schema = {
        "properties": {
            "intangible_assets": {
                "title": "Intangible Assets",
                "type": "number"
            },
            "revenue": {
                "title": "Revenue",
                "type": "number"
            },
            "current_liabilities": {
                "title": "Current Liabilities",
                "type": "number"
            },
            "total_liabilities": {
                "title": "Total Liabilities",
                "type": "number"
            }
        },
        "required": [
            "intangible_assets",
            "revenue",
            "current_liabilities",
            "total_liabilities"
        ],
        "title": "Response",
        "type": "object"
    }

    agent = get_or_create_agent("data-extractor", schema)
    print(agent)

    return {
        "msg": "ok"
    }
Originally created by @Antigaprime on GitHub (May 16, 2025). **Describe the bug** Methods for creating, deleting, fetching, etc, agents for use with LlamaExtract never complete when working with the python SDK in Google Cloud functions. **Client:** - Python SDK Library - `Python 3.13 (Ubuntu 22)` **Additional context** Any operations that involve agents never complete. Running the exact same code locally works fine. Sample code: ##### requirements.py ``` functions-framework==3.* llama-cloud-services==0.6.22 ``` ##### main.py ``` import functions_framework from llama_cloud_services import LlamaExtract extractor = LlamaExtract( verbose=True, ) def get_or_create_agent(name: str, schema: dict): try: agent = extractor.create_agent(name=name, data_schema=schema) except Exception as e: print(f"Error creating agent (might already exist): {e}") agent = extractor.get_agent(name=name) agent.data_schema = schema return agent @functions_framework.http def main(request): """HTTP Cloud Function. Args: request (flask.Request): The request object. <https://flask.palletsprojects.com/en/1.1.x/api/#incoming-request-data> Returns: The response text, or any set of values that can be turned into a Response object using `make_response` <https://flask.palletsprojects.com/en/1.1.x/api/#flask.make_response>. """ schema = { "properties": { "intangible_assets": { "title": "Intangible Assets", "type": "number" }, "revenue": { "title": "Revenue", "type": "number" }, "current_liabilities": { "title": "Current Liabilities", "type": "number" }, "total_liabilities": { "title": "Total Liabilities", "type": "number" } }, "required": [ "intangible_assets", "revenue", "current_liabilities", "total_liabilities" ], "title": "Response", "type": "object" } agent = get_or_create_agent("data-extractor", schema) print(agent) return { "msg": "ok" } ```
yindo added the bug label 2026-02-16 00:17:57 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#477
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?