注入火山引擎大模型的接口代码

config.py

@@ -198,6 +198,12 @@ ZHIPUAI_API_KEY = ""
 ZHIPUAI_MODEL = "chatglm_turbo"
 
 
+# # 火山引擎YUNQUE大模型
+# YUNQUE_SECRET_KEY = ""
+# YUNQUE_ACCESS_KEY = ""
+# YUNQUE_MODEL = ""
+
+
 # Claude API KEY
 ANTHROPIC_API_KEY = ""
 

request_llms/bridge_all.py

@@ -594,6 +594,23 @@ if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
         })
     except:
         print(trimmed_format_exc())
+# if "skylark" in AVAIL_LLM_MODELS:
+#     try:
+#         from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui
+#         from .bridge_skylark2 import predict as skylark_ui
+#         model_info.update({
+#             "skylark": {
+#                 "fn_with_ui": skylark_ui,
+#                 "fn_without_ui": skylark_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")

request_llms/bridge_skylark2.py

@@ -0,0 +1,67 @@
+import time
+from toolbox import update_ui, get_conf, update_ui_lastest_msg
+from toolbox import check_packages, report_exception
+
+model_name = '云雀大模型'
+
+def validate_key():
+    YUNQUE_SECRET_KEY = get_conf("YUNQUE_SECRET_KEY")
+    if YUNQUE_SECRET_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YUNQUE_SECRET_KEY')
+
+    from .com_skylark2api import YUNQUERequestInstance
+    sri = YUNQUERequestInstance()
+    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)
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        check_packages(["zhipuai"])
+    except:
+        yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
+                                         chatbot=chatbot, history=history, delay=0)
+        return
+
+    if validate_key() is False:
+        yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置HUOSHAN_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_skylark2api import YUNQUERequestInstance
+    sri = YUNQUERequestInstance()
+    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)

request_llms/com_skylark2api.py

@@ -0,0 +1,95 @@
+from toolbox import get_conf
+import threading
+import logging
+import os
+
+timeout_bot_msg = '[Local Message] Request timeout. Network error.'
+#os.environ['VOLC_ACCESSKEY'] = ''
+#os.environ['VOLC_SECRETKEY'] = ''
+
+class YUNQUERequestInstance():
+    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
+        from volcengine.maas import MaasService, MaasException
+
+        maas = MaasService('maas-api.ml-platform-cn-beijing.volces.com', 'cn-beijing')
+
+        YUNQUE_SECRET_KEY, YUNQUE_ACCESS_KEY,YUNQUE_MODEL = get_conf("YUNQUE_SECRET_KEY", "YUNQUE_ACCESS_KEY","YUNQUE_MODEL")
+        maas.set_ak(YUNQUE_ACCESS_KEY) #填写 VOLC_ACCESSKEY
+        maas.set_sk(YUNQUE_SECRET_KEY) #填写 'VOLC_SECRETKEY'
+
+        self.result_buf = ""
+
+        req = {
+        "model": {
+            "name": YUNQUE_MODEL,
+            "version": "1.0", # use default version if not specified.
+        },
+        "parameters": {
+            "max_new_tokens": 4000,  # 输出文本的最大tokens限制
+            "min_new_tokens": 1,  # 输出文本的最小tokens限制
+            "temperature": llm_kwargs['temperature'],  # 用于控制生成文本的随机性和创造性，Temperature值越大随机性越大，取值范围0~1
+            "top_p": llm_kwargs['top_p'],  # 用于控制输出tokens的多样性，TopP值越大输出的tokens类型越丰富，取值范围0~1
+            "top_k": 0,  # 选择预测值最大的k个token进行采样，取值范围0-1000，0表示不生效
+            "max_prompt_tokens": 4000,  # 最大输入 token 数，如果给出的 prompt 的 token 长度超过此限制，取最后 max_prompt_tokens 个 token 输入模型。
+        },
+            "messages": self.generate_message_payload(inputs, llm_kwargs, history, system_prompt)
+        }
+
+        response = maas.stream_chat(req)
+
+        for resp in response:
+            self.result_buf += resp.choice.message.content
+            yield self.result_buf
+        '''
+        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):
+        from volcengine.maas import ChatRole
+        conversation_cnt = len(history) // 2
+        messages = [{"role": ChatRole.USER, "content": system_prompt},
+                    {"role": ChatRole.ASSISTANT, "content": "Certainly!"}]
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = {}
+                what_i_have_asked["role"] = ChatRole.USER
+                what_i_have_asked["content"] = history[index]
+                what_gpt_answer = {}
+                what_gpt_answer["role"] = ChatRole.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"] = ChatRole.USER
+        what_i_ask_now["content"] = inputs
+        messages.append(what_i_ask_now)
+        return messages