Koshik Debanath
Koshik Debanath
Issue #284 , where the API failed to handle preflight OPTIONS requests, causing failures in direct client-to-API communications from browsers. The FastAPI application now includes CORSMiddleware, allowing proper handling of...
Fix TypeError: '<' not supported between instances of 'NoneType' and 'int' in embeddings_wrappers.py
This pull request fixes the issue where a TypeError occurs due to a comparison between NoneType and int The error was happening in the `_set_embeddings_metrics `function when recording token counts....
This PR supports tracking and logging prompt caching(#1838) metrics in the OpenTelemetry Anthropic instrumentation. Specifically, it captures and logs the `cache_creation_input_tokens` and `cache_read_input_tokens` fields from the API response. This enhancement...
Related to #1021 Add a "Copy References" button to the references pane in the web app. * **ReferencePanel Component** - Import `Clipboard` icon and `Button` component. - Add a "Copy...
Fixes #1689 Add support for OpenAI's batch completions API. * **Instrumentation**: Update `packages/opentelemetry-instrumentation-openai/opentelemetry/instrumentation/openai/__init__.py` to add support for batch completions in the `OpenAIInstrumentor` class. Import necessary modules and wrap the `create_batch`...
Fix Bug Report: Whole message history is stringified into a single 'user prompt' #2513 1. Bug Analysis Current Behavior Messages from chat history are combined into single string All roles...
From the transcript can we also have speaker diarization?
Can I use Qwen/Qwen2-VL-7B-Instruct model with images? Is yes how? Here is my code: ``` response = client.chat.completions.create( model="Qwen/Qwen2-VL-7B-Instruct", messages=[ { "role": "user", "content": [ { "type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",...
# I am submitting a new Community Plugin - [x] I attest that I have done my best to deliver a high-quality plugin, am proud of the code I have...