Berkin Güler

TRT Inference Not Working [volta_trt_flash]

6

``` [E] 3: [executionContext.cpp::validateInputBindings::1831] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::validateInputBindings::1831, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [2,4,64,96] for bindings[0] exceed min ~ max range...

[Bug]: Missing script initializations in --nowebui mode

1

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What happened? ControlNet extension (https://github.com/Mikubill/sd-webui-controlnet) defines its own...

KeyError: 'content' in OpenAILLMContext.from_messages when UserIdleProcessor and function calling used together

2

I have the following pipeline definition: ```python context = OpenAILLMContext(messages, tools) tma_in = LLMUserContextAggregator(context) tma_out = LLMAssistantContextAggregator(context) user_idle = UserIdleProcessor(callback=..., timeout=10.0) pipeline = Pipeline([ transport.input(), user_idle, tma_in, llm, tts, transport.output(),...

AnthropicLLMService exception

1

`pipecat.services.anthropic:_process_context:126 - AnthropicLLMService#0 exception: Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'messages: roles must alternate between "user" and "assistant", but found multiple "user" roles in a row'}}`...

Anthropic Prompt Caching Example

1

Can you add an example using the prompt caching?