feat(rag): make embedding and retrieving available

pkg/provider/modelmgr/requester.py

@@ -101,18 +101,18 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
     async def invoke_embedding(
         self,
         model: RuntimeEmbeddingModel,
-        input_text: str,
+        input_text: list[str],
         extra_args: dict[str, typing.Any] = {},
-    ) -> list[float]:
+    ) -> list[list[float]]:
         """调用 Embedding API
 
         Args:
             query (core_entities.Query): 请求上下文
             model (RuntimeEmbeddingModel): 使用的模型信息
-            input_text (str): 输入文本
+            input_text (list[str]): 输入文本
             extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
 
         Returns:
-            list[float]: 返回的 embedding 向量
+            list[list[float]]: 返回的 embedding 向量
         """
         pass

pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -145,9 +145,9 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
     async def invoke_embedding(
         self,
         model: requester.RuntimeEmbeddingModel,
-        input_text: str,
+        input_text: list[str],
         extra_args: dict[str, typing.Any] = {},
-    ) -> list[float]:
+    ) -> list[list[float]]:
         """调用 Embedding API"""
         self.client.api_key = model.token_mgr.get_token()
 
@@ -163,7 +163,8 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
 
         try:
             resp = await self.client.embeddings.create(**args)
-            return resp.data[0].embedding
+
+            return [d.embedding for d in resp.data]
         except asyncio.TimeoutError:
             raise errors.RequesterError('请求超时')
         except openai.BadRequestError as e: