Speedway1

Anyone successful with Radeon / AMD? (e.g.7900)

5

Has anyone successfully run this on Radeon/AMD?

NameError: name 'pipe' is not defined

6

Running with gradio, getting this error: Traceback (most recent call last): File "/data/misc/storydiffusion_env/lib/python3.11/site-packages/gradio/queueing.py", line 501, in call_prediction output = await route_utils.call_process_api( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/misc/storydiffusion_env/lib/python3.11/site-packages/gradio/route_utils.py", line 258, in call_process_api output =...

Bug fixes in utils/utils.py

3

Utils has problems with text generation due to deprecated parameters. Here are two bug fixes that I put in: 38c38 < width, _ = draw.textsize(test_line, font=font) --- > width, _...

Different LLM sources for "SMART" and "FAST".

1

We want to use our locally hosted Ollama Llama 3.1 LLM for the "fast" LLM but use Groq, OpenAI or Anthropic for the "smart" LLM. Has anyone successfully achieved mixing...

Crashes instead of displaying "Could not find any answers for this topic" when it wasn't able to find any relavant information.

6

For topics that return no results, it crashed rather than put out a meaningful error. From the logs: Of course, the information I've gleaned from your data is quite limited,...

Different provider for FAST and SMART LLMs

2

For each of the models used, is it possible to specify their own LLM provider? This is especially helpful with locally hosted models where the "smart" LLM can be hosted...

Expose "reason for rejection in invoice API end point.

1

**Background context** When the invoice status changes to "rejected" there is a corresponding reason for the rejection entered into the "reason for rejection" field on Reapit. However, this field hasn't...