ivanwu/jarvis-models
1
0
Fork 0
mirror of https://github.com/BoardWare-Genius/jarvis-models.git synced 2025-12-13 16:53:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

update chat

Browse Source
This commit is contained in:
ACBBZ
2024-05-24 03:14:52 +00:00
parent edd2f89056
commit 6c0af3ac35
1 changed files with 53 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
src/blackbox/chat.py
View File

@ -28,54 +28,10 @@ class Chat(Blackbox):
# model_name有 Qwen1.5-14B-Chat , internlm2-chat-20b
@logging_time(logger=logger)
def processing(self, model_name, prompt, template, context: list, temperature, top_p, n, max_tokens,stop,frequency_penalty,presence_penalty) -> str:
if context == None:
context = []
# gpt-4， gpt-3.5-turbo
if re.search(r"gpt", model_name):
url = 'https://api.openai.com/v1/completions'
key = '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'
else:
url = 'http://120.196.116.194:48892/v1/chat/completions'
key = 'YOUR_API_KEY'
prompt_template = [
{"role": "system", "content": template},
]
chat_inputs={
"model": model_name,
"messages": prompt_template + context + [
{
"role": "user",
"content": prompt
}
],
"temperature": temperature,
"top_p": top_p,
"n": n,
"max_tokens": max_tokens,
"frequency_penalty": frequency_penalty,
"presence_penalty": presence_penalty,
"stop": stop
}
header = {
'Content-Type': 'application/json',
'Authorization': "Bearer " + key
}
fastchat_response = requests.post(url, json=chat_inputs, headers=header)
return fastchat_response.json()["choices"][0]["message"]["content"]
async def fast_api_handler(self, request: Request) -> Response:
try:
data = await request.json()
except:
return JSONResponse(content={"error": "json parse error"}, status_code=status.HTTP_400_BAD_REQUEST)
def processing(self, *args, **kwargs) -> str:
data = args[0]
user_model_name = data.get("model_name")
user_context = data.get("context")
user_question = data.get("question")
@ -88,6 +44,9 @@ class Chat(Blackbox):
user_frequency_penalty = data.get("frequency_penalty")
user_presence_penalty = data.get("presence_penalty")
if user_context == None:
user_context = []
if user_question is None:
return JSONResponse(content={"error": "question is required"}, status_code=status.HTTP_400_BAD_REQUEST)
@ -119,5 +78,50 @@ class Chat(Blackbox):
user_presence_penalty = 0.8
return JSONResponse(content={"response": self.processing(user_model_name, user_question, user_template, user_context,
user_temperature, user_top_p, user_n, user_max_tokens,user_stop,user_frequency_penalty,user_presence_penalty)}, status_code=status.HTTP_200_OK)
# gpt-4， gpt-3.5-turbo
if re.search(r"gpt", user_model_name):
url = 'https://api.openai.com/v1/completions'
key = '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'
else:
url = 'http://120.196.116.194:48892/v1/chat/completions'
key = 'YOUR_API_KEY'
prompt_template = [
{"role": "system", "content": user_template},
]
chat_inputs={
"model": user_model_name,
"messages": prompt_template + user_context + [
{
"role": "user",
"content": user_question
}
],
"temperature": user_temperature,
"top_p": user_top_p,
"n": user_n,
"max_tokens": user_max_tokens,
"frequency_penalty": user_frequency_penalty,
"presence_penalty": user_presence_penalty,
"stop": user_stop
}
header = {
'Content-Type': 'application/json',
'Authorization': "Bearer " + key
}
fastchat_response = requests.post(url, json=chat_inputs, headers=header)
return fastchat_response.json()["choices"][0]["message"]["content"]
async def fast_api_handler(self, request: Request) -> Response:
try:
data = await request.json()
except:
return JSONResponse(content={"error": "json parse error"}, status_code=status.HTTP_400_BAD_REQUEST)
setting: dict = data.get("settings")
return JSONResponse(content={"response": self.processing(setting)}, status_code=status.HTTP_200_OK)