Emerson Gomes
Emerson Gomes
While trying to convert from Keras, I get the following error: ``` Traceback (most recent call last): File "C:\Users\emers\OneDrive\Documents\Code\ml4\.conda\lib\site-packages\tf2onnx\tf_loader.py", line 218, in from_trackable frozen_graph = from_function(concrete_func, inputs, outputs, large_model) File...
Today, a image generation requires a second call to an external Azure Endpoint in order to retrieve the generated image. This won't work in air-gapped system as they will not...
Currently, the confluence connector is unable to parse pageIds for Short URLs, in the format `/display//` This kind of URL requires an extra call to the Confluence API in order...
Hi, We had one of our connectors stuck in a failure loop. This created a side effect of the attempt index becoming too large and making the connector inaccesible from...
That's one of the features we're missing, currently supported by ChatGPT. Overall, would be nice to have a generic mechanism that could support other rendering engines, such as `mermaid`. Perhaps...
User provided a non-existing space name. However the connector indexing status shows up as "Succeeded" (for 0 documents) instead of failing with the actual error message (No space with key:...
## Description [This allows a custom timeout value to be set for the OpenAI Client] ## How Has This Been Tested? [Indexing done after change using OpenAI embedding model] ##...
During heavy load periods, internal calls to the `inference-model-server` can timeout before the component is able to respond the request. Timeout values used by the `httpx` client should be made...
## Description This allows the `httpx` client timeout values to be customized. ## How Has This Been Tested? [Indexing done after change] ## Accepted Risk [N/A] ## Related Issue(s) Fixes...
During a Jira indexing: ``` Traceback (most recent call last): File "/app/danswer/background/indexing/run_indexing.py", line 219, in _run_indexing new_docs, total_batch_chunks = indexing_pipeline( ^^^^^^^^^^^^^^^^^^ File "/app/danswer/indexing/indexing_pipeline.py", line 160, in index_doc_batch_with_handler r = index_doc_batch(...