aws-samples / aws-samples/llm-apps-workshop
Magnum adapter issue in the lambda functions
- Dominant language
- HTML
- Stars
- 113
- Forks
- 35
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
When I try to call the lambda function deployed by the stack (as explained in the readme)
```
curl -X POST "https://replace-with-your-api-gw-url/prod/api/v1/llm/rag" -H "accept: application/json" -H "Content-Type: application/json" -d "{\"q\":\"Which versions of XGBoost does SageMaker support?\"}"
```
I always get a 500 with the following log lines in the cloud watch:
```
{
"errorMessage": "'requestContext'",
"errorType": "KeyError",
"requestId": "889fc5a4-07df-40f1-9c69-3725cca2046e",
"stackTrace": [
" File \"/var/task/mangum/adapter.py\", line 110, in __call__\n return self.handler(event, context)\n",
" File \"/var/task/mangum/adapter.py\", line 130, in handler\n if \"eventType\" in event[\"requestContext\"]:\n"
]
}
```
It's pointed out [here](https://stackoverflow.com/questions/63710044/keyerror-requestcontext-fastapi-mangum-serverless) that it can be related to the `magnum` adapter. Can this be fixed in the repo?
Thanks in advance.
/Reza
Contributor guide
Assessment
This issue has not been assessed yet.