Azure-Samples
[BUG] Index Building failed
Describe the bug
Depoyment completed successfully. Facing issue while building an index. Index completion stucks at 18% and then fails.
log error:
{
'type': 'on_workflow_start',
'data': 'Index: book-graph-index1 -- Workflow (1/11): create_base_text_units started.',
'details': {
'workflow_name': 'create_base_text_units',
'index_name': 'book-graph-index1',
},
}
{
'type': 'on_workflow_end',
'data': 'Index: book-graph-index1 -- Workflow (1/11): create_base_text_units complete.',
'details': {
'workflow_name': 'create_base_text_units',
'index_name': 'book-graph-index1',
},
}
{
'type': 'on_workflow_start',
'data': 'Index: book-graph-index1 -- Workflow (2/11): create_final_documents started.',
'details': {
'workflow_name': 'create_final_documents',
'index_name': 'book-graph-index1',
},
}
{
'type': 'on_workflow_end',
'data': 'Index: book-graph-index1 -- Workflow (2/11): create_final_documents complete.',
'details': {
'workflow_name': 'create_final_documents',
'index_name': 'book-graph-index1',
},
}
{
'type': 'on_workflow_start',
'data': 'Index: book-graph-index1 -- Workflow (3/11): extract_graph started.',
'details': {
'workflow_name': 'extract_graph',
'index_name': 'book-graph-index1',
},
}
{
'type': 'error',
'data': 'Error Invoking LLM',
'cause': "Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}",
'stack': (
'Traceback (most recent call last):\n'
' File "/usr/local/lib/python3.10/site-packages/fnllm/base/base.py", line 112, in call\n'
' return await self._invoke(prompt, **kwargs)\n'
' File "/usr/local/lib/python3.10/site-packages/fnllm/base/base.py", line 128, in _invoke\n'
' return await self._decorated_target(prompt, **kwargs)\n'
' File "/usr/local/lib/python3.10/site-packages/fnllm/services/json.py", line 71, in invoke\n'
' return await delegate(prompt, **kwargs)\n'
' File "/usr/local/lib/python3.10/site-packages/fnllm/services/retryer.py", line 109, in invoke\n'
' result = await execute_with_retry()\n'
' File "/usr/local/lib/python3.10/site-packages/fnllm/services/retryer.py", line 93, in execute_with_retry\n'
' async for a in AsyncRetrying(\n'
' File "/usr/local/lib/python3.10/site-packages/tenacity/asyncio/init.py", line 166, in anext\n'
' do = await self.iter(retry_state=self._retry_state)\n'
' File "/usr/local/lib/python3.10/site-packages/tenacity/asyncio/init.py", line 153, in iter\n'
' result = await action(retry_state)\n'
' File "/usr/local/lib/python3.10/site-packages/tenacity/_utils.py", line 99, in inner\n'
' return call(*args, **kwargs)\n'
' File "/usr/local/lib/python3.10/site-packages/tenacity/init.py", line 400, in
To Reproduce 1-Quickstart.ipynb def build_index( storage_name: str, index_name: str, ) -> requests.Response: """Create a search index. This function kicks off a job that builds a knowledge graph index from files located in a blob storage container. """ url = endpoint + "/index" return requests.post( url, params={ "index_container_name": index_name, "storage_container_name": storage_name, }, headers=headers, ) response = build_index(storage_name=storage_name, index_name=index_name) print(response) if response.ok: print(response.text) else: print(f"Failed to submit job.\nStatus: {response.text}")
#Check status of indexing job def index_status(index_name: str) -> requests.Response: url = endpoint + f"/index/status/{index_name}" return requests.get(url, headers=headers)
response = index_status(index_name) pprint(response.json())
Expected behavior Indexing should complete
Additional context deployment parameters: AI_SEARCH_AUDIENCE="https://search.azure.com" AISEARCH_ENDPOINT_SUFFIX="search.windows.net" APIM_NAME="" APIM_TIER="Developer" CLOUD_NAME="AzurePublicCloud" GRAPHRAG_IMAGE="graphrag:backend" PUBLISHER_EMAIL="[email protected]" PUBLISHER_NAME="publisher" RESOURCE_BASE_NAME="" COGNITIVE_SERVICES_AUDIENCE="https://cognitiveservices.azure.com/.default" CONTAINER_REGISTRY_LOGIN_SERVER="" GRAPHRAG_API_BASE="" GRAPHRAG_API_VERSION="2023-03-15-preview" GRAPHRAG_LLM_MODEL="gpt-4" GRAPHRAG_LLM_MODEL_VERSION="turbo-2024-04-09" GRAPHRAG_LLM_DEPLOYMENT_NAME="gpt-4" GRAPHRAG_LLM_MODEL_QUOTA="80" GRAPHRAG_EMBEDDING_MODEL="text-embedding-ada-002" GRAPHRAG_EMBEDDING_MODEL_VERSION="2" GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME="text-embedding-ada-002" GRAPHRAG_EMBEDDING_MODEL_QUOTA="300"
I'm encountering the same issue where the indexing job consistently fails at 18% during the extract_graph workflow step. The job successfully completes the create_base_text_units and create_final_documents steps, but then fails with the following error:
openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
I deployed the solution using the provided scripts, and the deployment completed without errors. I uploaded .txt files using the upload_files() function in the notebook, which returned a 200 OK. I then triggered indexing with build_index(), which responded with Indexing job scheduled.
The model names and deployment names (e.g., gpt-4, text-embedding-ada-002) in my Azure OpenAI resource match what's set in the environment, and both are successfully deployed. However, it's unclear if the backend is referencing them correctly during the LLM invocation.
This seems like a misconfiguration or missing environment variable in the deployed app. Any advice on how to verify which AOAI deployment is actually being called at runtime—or how to debug this further—would be much appreciated.
I got the same error. The progress stops at 18.18%. I see
"openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}\n"
in the logs.
