增加本地大模型ollama支持

config.yaml

@@ -44,7 +44,7 @@ VAD:
     min_silence_duration_ms: 700  # 如果说话停顿比较长，可以把这个值设置大一些
 
 LLM:
-  # 当前支持的type为openai、dify，可自行适配
+  # 当前支持的type为openai、dify、ollama，可自行适配
   AliLLM:
     # 定义LLM API类型
     type: openai
@@ -67,6 +67,11 @@ LLM:
     model_name: glm-4-flash
     url: https://open.bigmodel.cn/api/paas/v4/
     api_key: 你的bigmodel api key
+  OllamaLLM:
+    # 定义LLM API类型
+    type: ollama
+    model_name: qwen2.5 #  使用的模型名称，需要预先使用ollama pull下载
+    base_url: http://localhost:11434  # Ollama服务地址
   DifyLLM:
     # 定义LLM API类型
     type: dify

core/providers/llm/ollama/ollama.py

@@ -0,0 +1,45 @@
+import logging
+import requests, json
+from core.providers.llm.base import LLMProviderBase
+
+logger = logging.getLogger(__name__)
+
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+
+        self.model_name = config.get("model_name")
+        self.base_url = config.get("base_url", "http://localhost:11434")
+
+    def response(self, session_id, dialogue):        
+        try:
+            # Convert dialogue format to Ollama format
+            prompt = ""
+            for msg in dialogue:
+                if msg["role"] == "system":
+                    prompt += f"System: {msg['content']}\n"
+                elif msg["role"] == "user":
+                    prompt += f"User: {msg['content']}\n"
+                elif msg["role"] == "assistant":
+                    prompt += f"Assistant: {msg['content']}\n"
+
+            # Make request to Ollama API
+            response = requests.post(
+                f"{self.base_url}/api/generate",
+                json={
+                    "model": self.model_name,
+                    "prompt": prompt,
+                    "stream": True
+                },
+                stream=True
+            )
+
+            for line in response.iter_lines():
+                if line:
+                    json_response = json.loads(line)
+                    if "response" in json_response:
+                        yield json_response["response"]
+
+        except Exception as e:
+            logger.error(f"Error in Ollama response generation: {e}")
+            yield "【Ollama服务响应异常】"