Compatibility issues with Chinese and slow response speed. #100
Description
There seem to be some compatibility issues with ChatBot, as an error occurs when inputting Chinese characters.
result = await app( # type: ignore[func-returns-value]
File "/usr/local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
return await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/fastapi/applications.py", line 276, in __call__
await super().__call__(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/applications.py", line 122, in __call__
await self.middleware_stack(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in __call__
raise exc
File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in __call__
await self.app(scope, receive, _send)
File "/usr/local/lib/python3.10/site-packages/starlette/middleware/cors.py", line 84, in __call__
await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
raise exc
File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
await self.app(scope, receive, sender)
File "/usr/local/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
raise e
File "/usr/local/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 718, in __call__
await route.handle(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle
await self.app(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 69, in app
await response(scope, receive, send)
File "/usr/local/lib/python3.10/site-packages/sse_starlette/sse.py", line 227, in __call__
async with anyio.create_task_group() as task_group:
File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 662, in __aexit__
raise exceptions[0]
File "/usr/local/lib/python3.10/site-packages/sse_starlette/sse.py", line 230, in wrap
await func()
File "/usr/local/lib/python3.10/site-packages/sse_starlette/sse.py", line 219, in stream_response
async for data in self.body_iterator:
File "/www/transcribe/ai-language-model/llama-cpp-python/examples/high_level_api/fastapi_server.py", line 215, in server_sent_events
for chat_chunk in chat_chunks:
File "/usr/local/lib/python3.10/site-packages/llama_cpp/llama.py", line 720, in _convert_text_completion_chunks_to_chat
for i, chunk in enumerate(chunks):
File "/usr/local/lib/python3.10/site-packages/llama_cpp/llama.py", line 482, in _create_completion
"text": text[start:].decode("utf-8"),
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe4 in position 0: unexpected end of data
In addition to that, I'm also experiencing some slow speed using the ggml-vicuna-13b-1.1-q4_1.bin model. Although I noticed that the GPU memory usage is not very high, so I'm not sure what could be causing this.
Nonetheless, I would like to express my gratitude to the author for developing such a great interface that mimics OpenAI. If only the response speed could be faster.