feat: support weixin ernie-bot-4 and chat mode (#1375)

api/core/model_providers/models/llm/wenxin_model.py

@@ -6,17 +6,16 @@ from langchain.schema import LLMResult
 
 from core.model_providers.error import LLMBadRequestError
 from core.model_providers.models.llm.base import BaseLLM
-from core.model_providers.models.entity.message import PromptMessage, MessageType
+from core.model_providers.models.entity.message import PromptMessage
 from core.model_providers.models.entity.model_params import ModelMode, ModelKwargs
 from core.third_party.langchain.llms.wenxin import Wenxin
 
 
 class WenxinModel(BaseLLM):
-    model_mode: ModelMode = ModelMode.COMPLETION
+    model_mode: ModelMode = ModelMode.CHAT
 
     def _init_client(self) -> Any:
         provider_model_kwargs = self._to_model_kwargs_input(self.model_rules, self.model_kwargs)
-        # TODO load price_config from configs(db)
         return Wenxin(
             model=self.name,
             streaming=self.streaming,
@@ -38,7 +37,13 @@ class WenxinModel(BaseLLM):
         :return:
         """
         prompts = self._get_prompt_from_messages(messages)
-        return self._client.generate([prompts], stop, callbacks)
+
+        generate_kwargs = {'stop': stop, 'callbacks': callbacks, 'messages': [prompts]}
+
+        if 'functions' in kwargs:
+            generate_kwargs['functions'] = kwargs['functions']
+
+        return self._client.generate(**generate_kwargs)
 
     def get_num_tokens(self, messages: List[PromptMessage]) -> int:
         """
@@ -48,7 +53,7 @@ class WenxinModel(BaseLLM):
         :return:
         """
         prompts = self._get_prompt_from_messages(messages)
-        return max(self._client.get_num_tokens(prompts), 0)
+        return max(self._client.get_num_tokens_from_messages(prompts), 0)
 
     def _set_model_kwargs(self, model_kwargs: ModelKwargs):
         provider_model_kwargs = self._to_model_kwargs_input(self.model_rules, model_kwargs)
@@ -58,3 +63,7 @@ class WenxinModel(BaseLLM):
 
     def handle_exceptions(self, ex: Exception) -> Exception:
         return LLMBadRequestError(f"Wenxin: {str(ex)}")
+
+    @property
+    def support_streaming(self):
+        return True

api/core/model_providers/providers/wenxin_provider.py

@@ -2,6 +2,8 @@ import json
 from json import JSONDecodeError
 from typing import Type
 
+from langchain.schema import HumanMessage
+
 from core.helper import encrypter
 from core.model_providers.models.base import BaseProviderModel
 from core.model_providers.models.entity.model_params import ModelKwargsRules, KwargRule, ModelType, ModelMode
@@ -23,20 +25,25 @@ class WenxinProvider(BaseModelProvider):
     def _get_fixed_model_list(self, model_type: ModelType) -> list[dict]:
         if model_type == ModelType.TEXT_GENERATION:
             return [
+                {
+                    'id': 'ernie-bot-4',
+                    'name': 'ERNIE-Bot-4',
+                    'mode': ModelMode.CHAT.value,
+                },
                 {
                     'id': 'ernie-bot',
                     'name': 'ERNIE-Bot',
-                    'mode': ModelMode.COMPLETION.value,
+                    'mode': ModelMode.CHAT.value,
                 },
                 {
                     'id': 'ernie-bot-turbo',
                     'name': 'ERNIE-Bot-turbo',
-                    'mode': ModelMode.COMPLETION.value,
+                    'mode': ModelMode.CHAT.value,
                 },
                 {
                     'id': 'bloomz-7b',
                     'name': 'BLOOMZ-7B',
-                    'mode': ModelMode.COMPLETION.value,
+                    'mode': ModelMode.CHAT.value,
                 }
             ]
         else:
@@ -68,11 +75,12 @@ class WenxinProvider(BaseModelProvider):
         :return:
         """
         model_max_tokens = {
+            'ernie-bot-4': 4800,
             'ernie-bot': 4800,
             'ernie-bot-turbo': 11200,
         }
 
-        if model_name in ['ernie-bot', 'ernie-bot-turbo']:
+        if model_name in ['ernie-bot-4', 'ernie-bot', 'ernie-bot-turbo']:
             return ModelKwargsRules(
                 temperature=KwargRule[float](min=0.01, max=1, default=0.95, precision=2),
                 top_p=KwargRule[float](min=0.01, max=1, default=0.8, precision=2),
@@ -111,7 +119,7 @@ class WenxinProvider(BaseModelProvider):
                 **credential_kwargs
             )
 
-            llm("ping")
+            llm([HumanMessage(content='ping')])
         except Exception as ex:
             raise CredentialsValidateFailedError(str(ex))
 

api/core/model_providers/rules/wenxin.json

@@ -5,6 +5,12 @@
     "system_config": null,
     "model_flexibility": "fixed",
     "price_config": {
+        "ernie-bot-4": {
+            "prompt": "0",
+            "completion": "0",
+            "unit": "0.001",
+            "currency": "RMB"
+        },
         "ernie-bot": {
             "prompt": "0.012",
             "completion": "0.012",