接入新模型

这个提交包含在:
binary-husky
2023-10-28 19:23:43 +08:00
父节点 cf085565a7
当前提交 127385b846
共有 18 个文件被更改,包括 253 次插入40 次删除

查看文件

@@ -483,6 +483,22 @@ if "llama2" in AVAIL_LLM_MODELS: # llama2
})
except:
print(trimmed_format_exc())
if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai
try:
from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
from .bridge_zhipu import predict as zhipu_ui
model_info.update({
"zhipuai": {
"fn_with_ui": zhipu_ui,
"fn_without_ui": zhipu_noui,
"endpoint": None,
"max_token": 4096,
"tokenizer": tokenizer_gpt35,
"token_cnt": get_token_num_gpt35,
}
})
except:
print(trimmed_format_exc())
# <-- 用于定义和切换多个azure模型 -->
AZURE_CFG_ARRAY, = get_conf("AZURE_CFG_ARRAY")

查看文件

@@ -155,13 +155,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收chatglm的回复
response = "[Local Message]: 等待ChatGLM响应中 ..."
response = "[Local Message] 等待ChatGLM响应中 ..."
for response in glm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待ChatGLM响应中 ...":
response = "[Local Message]: ChatGLM响应异常 ..."
if response == "[Local Message] 等待ChatGLM响应中 ...":
response = "[Local Message] ChatGLM响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -195,13 +195,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收chatglmft的回复
response = "[Local Message]: 等待ChatGLMFT响应中 ..."
response = "[Local Message] 等待ChatGLMFT响应中 ..."
for response in glmft_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待ChatGLMFT响应中 ...":
response = "[Local Message]: ChatGLMFT响应异常 ..."
if response == "[Local Message] 等待ChatGLMFT响应中 ...":
response = "[Local Message] ChatGLMFT响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -163,13 +163,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收jittorllms的回复
response = "[Local Message]: 等待jittorllms响应中 ..."
response = "[Local Message] 等待jittorllms响应中 ..."
for response in llama_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待jittorllms响应中 ...":
response = "[Local Message]: jittorllms响应异常 ..."
if response == "[Local Message] 等待jittorllms响应中 ...":
response = "[Local Message] jittorllms响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -163,13 +163,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收jittorllms的回复
response = "[Local Message]: 等待jittorllms响应中 ..."
response = "[Local Message] 等待jittorllms响应中 ..."
for response in pangu_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待jittorllms响应中 ...":
response = "[Local Message]: jittorllms响应异常 ..."
if response == "[Local Message] 等待jittorllms响应中 ...":
response = "[Local Message] jittorllms响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -163,13 +163,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收jittorllms的回复
response = "[Local Message]: 等待jittorllms响应中 ..."
response = "[Local Message] 等待jittorllms响应中 ..."
for response in rwkv_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待jittorllms响应中 ...":
response = "[Local Message]: jittorllms响应异常 ..."
if response == "[Local Message] 等待jittorllms响应中 ...":
response = "[Local Message] jittorllms响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -219,7 +219,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
moss_handle = None
return
else:
response = "[Local Message]: 等待MOSS响应中 ..."
response = "[Local Message] 等待MOSS响应中 ..."
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
@@ -238,7 +238,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == "[Local Message]: 等待MOSS响应中 ...":
response = "[Local Message]: MOSS响应异常 ..."
if response == "[Local Message] 等待MOSS响应中 ...":
response = "[Local Message] MOSS响应异常 ..."
history.extend([inputs, response.strip('<|MOSS|>: ')])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -199,7 +199,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
response = ""
if len(observe_window) >= 1: observe_window[0] = "[Local Message]: 等待NewBing响应中 ..."
if len(observe_window) >= 1: observe_window[0] = "[Local Message] 等待NewBing响应中 ..."
for response in newbingfree_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
if len(observe_window) >= 1: observe_window[0] = preprocess_newbing_out_simple(response)
if len(observe_window) >= 2:
@@ -212,7 +212,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
单线程方法
函数的说明请见 request_llms/bridge_all.py
"""
chatbot.append((inputs, "[Local Message]: 等待NewBing响应中 ..."))
chatbot.append((inputs, "[Local Message] 等待NewBing响应中 ..."))
global newbingfree_handle
if (newbingfree_handle is None) or (not newbingfree_handle.success):
@@ -231,13 +231,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
for i in range(len(history)//2):
history_feedin.append([history[2*i], history[2*i+1]] )
chatbot[-1] = (inputs, "[Local Message]: 等待NewBing响应中 ...")
response = "[Local Message]: 等待NewBing响应中 ..."
chatbot[-1] = (inputs, "[Local Message] 等待NewBing响应中 ...")
response = "[Local Message] 等待NewBing响应中 ..."
yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢,尚未完成全部响应,请耐心完成后再提交新问题。")
for response in newbingfree_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, preprocess_newbing_out(response))
yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢,尚未完成全部响应,请耐心完成后再提交新问题。")
if response == "[Local Message]: 等待NewBing响应中 ...": response = "[Local Message]: NewBing响应异常,请刷新界面重试 ..."
if response == "[Local Message] 等待NewBing响应中 ...": response = "[Local Message] NewBing响应异常,请刷新界面重试 ..."
history.extend([inputs, response])
logging.info(f'[raw_input] {inputs}')
logging.info(f'[response] {response}')

查看文件

@@ -158,8 +158,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
return
# 总结输出
response = f"[Local Message]: {model_name}响应异常 ..."
if response == f"[Local Message]: 等待{model_name}响应中 ...":
response = f"[Local Message]: {model_name}响应异常 ..."
response = f"[Local Message] {model_name}响应异常 ..."
if response == f"[Local Message] 等待{model_name}响应中 ...":
response = f"[Local Message] {model_name}响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -42,7 +42,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
yield from update_ui(chatbot=chatbot, history=history)
if validate_key() is False:
yield from update_ui_lastest_msg(lastmsg="[Local Message]: 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET", chatbot=chatbot, history=history, delay=0)
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET", chatbot=chatbot, history=history, delay=0)
return
if additional_fn is not None:
@@ -57,7 +57,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == f"[Local Message]: 等待{model_name}响应中 ...":
response = f"[Local Message]: {model_name}响应异常 ..."
if response == f"[Local Message] 等待{model_name}响应中 ...":
response = f"[Local Message] {model_name}响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -222,7 +222,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
response = ""
observe_window[0] = "[Local Message]: 等待Claude响应中 ..."
observe_window[0] = "[Local Message] 等待Claude响应中 ..."
for response in claude_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
observe_window[0] = preprocess_newbing_out_simple(response)
if len(observe_window) >= 2:
@@ -236,7 +236,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
单线程方法
函数的说明请见 request_llms/bridge_all.py
"""
chatbot.append((inputs, "[Local Message]: 等待Claude响应中 ..."))
chatbot.append((inputs, "[Local Message] 等待Claude响应中 ..."))
global claude_handle
if (claude_handle is None) or (not claude_handle.success):
@@ -255,14 +255,14 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
for i in range(len(history)//2):
history_feedin.append([history[2*i], history[2*i+1]])
chatbot[-1] = (inputs, "[Local Message]: 等待Claude响应中 ...")
response = "[Local Message]: 等待Claude响应中 ..."
chatbot[-1] = (inputs, "[Local Message] 等待Claude响应中 ...")
response = "[Local Message] 等待Claude响应中 ..."
yield from update_ui(chatbot=chatbot, history=history, msg="Claude响应缓慢,尚未完成全部响应,请耐心完成后再提交新问题。")
for response in claude_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt):
chatbot[-1] = (inputs, preprocess_newbing_out(response))
yield from update_ui(chatbot=chatbot, history=history, msg="Claude响应缓慢,尚未完成全部响应,请耐心完成后再提交新问题。")
if response == "[Local Message]: 等待Claude响应中 ...":
response = "[Local Message]: Claude响应异常,请刷新界面重试 ..."
if response == "[Local Message] 等待Claude响应中 ...":
response = "[Local Message] Claude响应异常,请刷新界面重试 ..."
history.extend([inputs, response])
logging.info(f'[raw_input] {inputs}')
logging.info(f'[response] {response}')

查看文件

@@ -0,0 +1,59 @@
import time
from toolbox import update_ui, get_conf, update_ui_lastest_msg
model_name = '智谱AI大模型'
def validate_key():
ZHIPUAI_API_KEY, = get_conf("ZHIPUAI_API_KEY")
if ZHIPUAI_API_KEY == '': return False
return True
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
"""
⭐多线程方法
函数的说明请见 request_llms/bridge_all.py
"""
watch_dog_patience = 5
response = ""
if validate_key() is False:
raise RuntimeError('请配置ZHIPUAI_API_KEY')
from .com_zhipuapi import ZhipuRequestInstance
sri = ZhipuRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
if len(observe_window) >= 1:
observe_window[0] = response
if len(observe_window) >= 2:
if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
return response
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
"""
⭐单线程方法
函数的说明请见 request_llms/bridge_all.py
"""
chatbot.append((inputs, ""))
yield from update_ui(chatbot=chatbot, history=history)
if validate_key() is False:
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
return
if additional_fn is not None:
from core_functional import handle_core_functionality
inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
# 开始接收回复
from .com_zhipuapi import ZhipuRequestInstance
sri = ZhipuRequestInstance()
for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == f"[Local Message] 等待{model_name}响应中 ...":
response = f"[Local Message] {model_name}响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)

查看文件

@@ -0,0 +1,67 @@
from toolbox import get_conf
import threading
import logging
timeout_bot_msg = '[Local Message] Request timeout. Network error.'
class ZhipuRequestInstance():
def __init__(self):
self.time_to_yield_event = threading.Event()
self.time_to_exit_event = threading.Event()
self.result_buf = ""
def generate(self, inputs, llm_kwargs, history, system_prompt):
# import _thread as thread
import zhipuai
ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
zhipuai.api_key = ZHIPUAI_API_KEY
self.result_buf = ""
response = zhipuai.model_api.sse_invoke(
model=ZHIPUAI_MODEL,
prompt=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
top_p=llm_kwargs['top_p'],
temperature=llm_kwargs['temperature'],
)
for event in response.events():
if event.event == "add":
self.result_buf += event.data
yield self.result_buf
elif event.event == "error" or event.event == "interrupted":
raise RuntimeError("Unknown error:" + event.data)
elif event.event == "finish":
yield self.result_buf
break
else:
raise RuntimeError("Unknown error:" + str(event))
logging.info(f'[raw_input] {inputs}')
logging.info(f'[response] {self.result_buf}')
return self.result_buf
def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
conversation_cnt = len(history) // 2
messages = [{"role": "user", "content": system_prompt}, {"role": "assistant", "content": "Certainly!"}]
if conversation_cnt:
for index in range(0, 2*conversation_cnt, 2):
what_i_have_asked = {}
what_i_have_asked["role"] = "user"
what_i_have_asked["content"] = history[index]
what_gpt_answer = {}
what_gpt_answer["role"] = "assistant"
what_gpt_answer["content"] = history[index+1]
if what_i_have_asked["content"] != "":
if what_gpt_answer["content"] == "":
continue
if what_gpt_answer["content"] == timeout_bot_msg:
continue
messages.append(what_i_have_asked)
messages.append(what_gpt_answer)
else:
messages[-1]['content'] = what_gpt_answer['content']
what_i_ask_now = {}
what_i_ask_now["role"] = "user"
what_i_ask_now["content"] = inputs
messages.append(what_i_ask_now)
return messages

查看文件

@@ -166,14 +166,14 @@ def get_local_llm_predict_fns(LLMSingletonClass, model_name):
history_feedin.append([history[2*i], history[2*i+1]] )
# 开始接收回复
response = f"[Local Message]: 等待{model_name}响应中 ..."
response = f"[Local Message] 等待{model_name}响应中 ..."
for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
chatbot[-1] = (inputs, response)
yield from update_ui(chatbot=chatbot, history=history)
# 总结输出
if response == f"[Local Message]: 等待{model_name}响应中 ...":
response = f"[Local Message]: {model_name}响应异常 ..."
if response == f"[Local Message] 等待{model_name}响应中 ...":
response = f"[Local Message] {model_name}响应异常 ..."
history.extend([inputs, response])
yield from update_ui(chatbot=chatbot, history=history)