Yi-Ting Chiu

Windows version "/api/generate" 404 not found

9

The "/api/generate" is not functioning and display 404 on the Windows version (not WSL), despite the Ollama server running and "/" being accessible. The same code works on the Ollama...

FunASR requires internet connection even if the models are downloaded and locally available

8

Check this issue https://github.com/modelscope/FunASR/issues/1897

## Environment - macOS 14.5, m1 pro - Python 3.11.9 ## Code Here is the code to reproduce the issue: ~~~python import pyttsx3 engine = pyttsx3.init() engine.save_to_file('I will speak this...

Add ZhipuAI provider integration to the python package. * Add `aisuite/providers/zhipuai_provider.py` implementing the `ZhipuaiProvider` class using the `zhipuai` library. * Update `ProviderFactory` in `aisuite/provider.py` to include ZhipuAI as a supported...

`graphiti-core` may be importing a package unintentionally

1

Hey I noticed that `graphiti-core` may be *importing a package unintentionally*. While working on a pull request to migrate `graphiti-core` from Poetry to uv, I ran into a circular import...

Fix: CypherTypeError: Property values can only be of primitive types or arrays thereof

1

## What’s Fixed ``` neo4j.exceptions.CypherTypeError: {code: Neo.ClientError.Statement.TypeError} {message: Property values can only be of primitive types or arrays thereof. Encountered: Map{summary -> Map{description -> String("Summary containing the important information about...

Current Docker setup appears broken

1

## Summary While working on a PR to migrate this project from Poetry to `uv`, I ran into a blocker unrelated to my changes: the current Docker setup in `main`...

Simplifying imports for llm_client and cross_encoder

2

**Why?** * It didn’t make sense to expose only `OpenAIClient` while omitting `OpenAIGenericClient`, `AnthropicClient`, `GeminiClient`, and `GroqClient`. This led to confusion for users. * A similar issue existed in `cross_encoder`,...

This pull request migrates the project from Poetry to UV, following the discussion in #420. **Note:** I have not updated the GitHub Actions workflows yet, as I’m less familiar with...

Making GPU acceleration for sherpa onnx work by default

1

## Current Behavior - Sherpa onnx is the default ASR engine in Open-LLM-VTuber project - It runs on CPU - Configuring GPU acceleration for it is non-trivial ## Goal -...