怎么设置自定义模型

[DivvSpace]

如果设置了相关链接，是哪里出了问题

[aotsukiqx]

看了看docker日志没把我愁死，query=fasdf&model=gpt3.5&ask_type=search&model_token=" "，第一个问题，没有使用配置的自定义模型名称（但是确实改了base url），第二个问题压根就没用设置的token，也就是除非你本地模型不做token验证才能用。

[huawuhen]

同样的问题，

[DivvSpace]

开个Discord,一块研究研究

[pirately]

可以直接修改free_ask_internet.py文件，调用ollama等自定义的。再通过第三方，比如nextchat调用本项目的端口就可以。或者把这个项目的接口加入one-api，当作单独的search模型调用。

[huawuhen]

可以直接修改free_ask_internet.py文件，调用ollama等自定义的。再通过第三方，比如nextchat调用本项目的端口就可以。或者把这个项目的接口加入one-api，当作单独的search模型调用。

关键是one-api无法接入

[pirately]

可以直接修改free_ask_internet.py文件，调用ollama等自定义的。再通过第三方，比如nextchat调用本项目的端口就可以。或者把这个项目的接口加入one-api，当作单独的search模型调用。

关键是one-api无法接入

可以的

利用one-api自定义search模型

nextchat客户端选择search模型

用search模型回答

[2451965602]

可以直接修改free_ask_internet.py文件，调用ollama等自定义的。再通过第三方，比如nextchat调用本项目的端口就可以。或者把这个项目的接口加入one-api，当作单独的search模型调用。

关键是one-api无法接入

可以的

利用one-api自定义search模型

nextchat客户端选择search模型

用search模型回答

用oneapi接入时报错，直接在free_ask_internet_ui里调用正常

model='search' messages=[ChatMessage(role='user', content='霍尔')] temperature=0.5 top_p=1.0 max_length=None stream=True
2024-04-14T12:19:39.928153497Z INFO:     172.17.0.2:53486 - "POST /v1/chat/completions?path=v1&path=chat&path=completions HTTP/1.1" 200 OK
2024-04-14T12:19:42.246322601Z ERROR:    Exception in ASGI application
2024-04-14T12:19:42.246345855Z Traceback (most recent call last):
2024-04-14T12:19:42.246348700Z   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 281, in __call__
2024-04-14T12:19:42.246350644Z     await wrap(partial(self.listen_for_disconnect, receive))
2024-04-14T12:19:42.246352237Z   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 270, in wrap
2024-04-14T12:19:42.246353910Z     await func()
2024-04-14T12:19:42.246355764Z   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 221, in listen_for_disconnect
2024-04-14T12:19:42.246357467Z     message = await receive()
2024-04-14T12:19:42.246359040Z   File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 535, in receive
2024-04-14T12:19:42.246360563Z     await self.message_event.wait()
2024-04-14T12:19:42.246362025Z   File "/usr/local/lib/python3.9/asyncio/locks.py", line 226, in wait
2024-04-14T12:19:42.246384008Z     await fut
2024-04-14T12:19:42.246386052Z asyncio.exceptions.CancelledError: Cancelled by cancel scope 7fd034609e20
2024-04-14T12:19:42.246387675Z 
2024-04-14T12:19:42.246389338Z During handling of the above exception, another exception occurred:
2024-04-14T12:19:42.246390851Z 
2024-04-14T12:19:42.246392423Z   + Exception Group Traceback (most recent call last):
2024-04-14T12:19:42.246393876Z   |   File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi
2024-04-14T12:19:42.246395479Z   |     result = await app(  # type: ignore[func-returns-value]
2024-04-14T12:19:42.246396932Z   |   File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 69, in __call__
2024-04-14T12:19:42.246398465Z   |     return await self.app(scope, receive, send)
2024-04-14T12:19:42.246399908Z   |   File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in __call__
2024-04-14T12:19:42.246401451Z   |     await super().__call__(scope, receive, send)
2024-04-14T12:19:42.246403034Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 123, in __call__
2024-04-14T12:19:42.246404597Z   |     await self.middleware_stack(scope, receive, send)
2024-04-14T12:19:42.246406019Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 186, in __call__
2024-04-14T12:19:42.246407552Z   |     raise exc
2024-04-14T12:19:42.246408945Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 164, in __call__
2024-04-14T12:19:42.246410457Z   |     await self.app(scope, receive, _send)
2024-04-14T12:19:42.246411900Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 85, in __call__
2024-04-14T12:19:42.246413483Z   |     await self.app(scope, receive, send)
2024-04-14T12:19:42.246415647Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 65, in __call__
2024-04-14T12:19:42.246417210Z   |     await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
2024-04-14T12:19:42.246418693Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
2024-04-14T12:19:42.246420236Z   |     raise exc
2024-04-14T12:19:42.246421689Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
2024-04-14T12:19:42.246423642Z   |     await app(scope, receive, sender)
2024-04-14T12:19:42.246425175Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 756, in __call__
2024-04-14T12:19:42.246426688Z   |     await self.middleware_stack(scope, receive, send)
2024-04-14T12:19:42.246428341Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 776, in app
2024-04-14T12:19:42.246432679Z   |     await route.handle(scope, receive, send)
2024-04-14T12:19:42.246434272Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 297, in handle
2024-04-14T12:19:42.246435945Z   |     await self.app(scope, receive, send)
2024-04-14T12:19:42.246437589Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 77, in app
2024-04-14T12:19:42.246439092Z   |     await wrap_app_handling_exceptions(app, request)(scope, receive, send)
2024-04-14T12:19:42.246440555Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
2024-04-14T12:19:42.246442088Z   |     raise exc
2024-04-14T12:19:42.246443631Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
2024-04-14T12:19:42.246454611Z   |     await app(scope, receive, sender)
2024-04-14T12:19:42.246456384Z   |   File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 75, in app
2024-04-14T12:19:42.246457907Z   |     await response(scope, receive, send)
2024-04-14T12:19:42.246459340Z   |   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 281, in __call__
2024-04-14T12:19:42.246460983Z   |     await wrap(partial(self.listen_for_disconnect, receive))
2024-04-14T12:19:42.246462426Z   |   File "/usr/local/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 678, in __aexit__
2024-04-14T12:19:42.246463979Z   |     raise BaseExceptionGroup(
2024-04-14T12:19:42.246465412Z   | exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
2024-04-14T12:19:42.246466874Z   +-+---------------- 1 ----------------
2024-04-14T12:19:42.246468317Z     | Traceback (most recent call last):
2024-04-14T12:19:42.246469760Z     |   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 270, in wrap
2024-04-14T12:19:42.246471292Z     |     await func()
2024-04-14T12:19:42.246473086Z     |   File "/usr/local/lib/python3.9/site-packages/sse_starlette/sse.py", line 251, in stream_response
2024-04-14T12:19:42.246474639Z     |     async for data in self.body_iterator:
2024-04-14T12:19:42.246476162Z     |   File "/usr/local/lib/python3.9/site-packages/starlette/concurrency.py", line 65, in iterate_in_threadpool
2024-04-14T12:19:42.246477724Z     |     yield await anyio.to_thread.run_sync(_next, as_iterator)
2024-04-14T12:19:42.246479187Z     |   File "/usr/local/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync
2024-04-14T12:19:42.246480720Z     |     return await get_async_backend().run_sync_in_worker_thread(
2024-04-14T12:19:42.246482293Z     |   File "/usr/local/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread
2024-04-14T12:19:42.246483836Z     |     return await future
2024-04-14T12:19:42.246486070Z     |   File "/usr/local/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 851, in run
2024-04-14T12:19:42.246492543Z     |     result = context.run(func, *args)
2024-04-14T12:19:42.246495790Z     |   File "/usr/local/lib/python3.9/site-packages/starlette/concurrency.py", line 54, in _next
2024-04-14T12:19:42.246499246Z     |     return next(iterator)
2024-04-14T12:19:42.246502452Z     |   File "/app/server.py", line 152, in predict
2024-04-14T12:19:42.246505558Z     |     for token in free_ask_internet.ask_internet(query=query):
2024-04-14T12:19:42.246508594Z     |   File "/app/free_ask_internet.py", line 204, in ask_internet
2024-04-14T12:19:42.246511669Z     |     prompt = gen_prompt(query,content_list,context_length_limit=6000,debug=debug)
2024-04-14T12:19:42.246514785Z     |   File "/app/free_ask_internet.py", line 108, in gen_prompt
2024-04-14T12:19:42.246517741Z     |     ref_content = [ item.get("content") for item in content_list]
2024-04-14T12:19:42.246534422Z     |   File "/app/free_ask_internet.py", line 108, in <listcomp>
2024-04-14T12:19:42.246538580Z     |     ref_content = [ item.get("content") for item in content_list]
2024-04-14T12:19:42.246540643Z     | AttributeError: 'list' object has no attribute 'get'
2024-04-14T12:19:42.246542277Z     +------------------------------------

[DivvSpace]

怎么设置页面都不一样😂

[pirately]

可以直接修改free_ask_internet.py文件，调用ollama等自定义的。再通过第三方，比如nextchat调用本项目的端口就可以。或者把这个项目的接口加入one-api，当作单独的search模型调用。

关键是one-api无法接入

可以的

用oneapi接入时报错，直接在free_ask_internet_ui里调用正常

free_ask_internet.py文件中的 219行，改content_list = search_web_ref(query,debug=debug)为conv_links, content_list = search_web_ref(query,debug=debug)。直接用python server.py在本地试。searxng模型，还有其他gpt或者glm模型用本地已经搭建好的，也就是38行和172行要改成本地的

[pirately]

怎么设置页面都不一样😂

我没有用freeaskinternet ui这个，我是把本项目当api调用的。

[huawuhen]

我知道问题出在哪里了，问了作者，他的接口不是标准的openai-api，需要你的one-api接口地址后面加个/v1/

[DivvSpace]

我知道问题出在哪里了，问了作者，他的接口不是标准的openai-api，需要你的one-api接口地址后面加个/v1/

一针见血的，有用的👍