Merge branch 'master' into frontier

request_llms/bridge_all.py

@@ -860,6 +860,15 @@ if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
+            },
+            "sparkv4":{
+                "fn_with_ui": spark_ui,
+                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
             }
         })
     except:

request_llms/com_sparkapi.py

@@ -67,6 +67,7 @@ class SparkRequestInstance():
         self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
         self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
         self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
+        self.gpt_url_v4 = "wss://spark-api.xf-yun.com/v4.0/chat"
 
         self.time_to_yield_event = threading.Event()
         self.time_to_exit_event = threading.Event()
@@ -94,6 +95,8 @@ class SparkRequestInstance():
             gpt_url = self.gpt_url_v3
         elif llm_kwargs['llm_model'] == 'sparkv3.5':
             gpt_url = self.gpt_url_v35
+        elif llm_kwargs['llm_model'] == 'sparkv4':
+            gpt_url = self.gpt_url_v4
         else:
             gpt_url = self.gpt_url
         file_manifest = []
@@ -194,6 +197,7 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
         "sparkv2": "generalv2",
         "sparkv3": "generalv3",
         "sparkv3.5": "generalv3.5",
+        "sparkv4": "4.0Ultra"
     }
     domains_select = domains[llm_kwargs['llm_model']]
     if file_manifest: domains_select = 'image'

request_llms/oai_std_model_template.py

@@ -44,7 +44,8 @@ def decode_chunk(chunk):
     try:
         chunk = json.loads(chunk[6:])
     except:
-        finish_reason = "JSON_ERROR"
+        respose = "API_ERROR"
+        finish_reason = chunk
     # 错误处理部分
     if "error" in chunk:
         respose = "API_ERROR"