feat:add dashscopeapi stream

fix:dify 64chunk yield

pkg/provider/runners/dashscopeapi.py

@@ -113,7 +113,14 @@ class DashScopeAPIRunner(runner.RequestRunner):
             #     "session_file_ids": ["FILE_ID1"],             # FILE_ID1 替换为实际的临时文件ID,逗号隔开多个
             # }
         )
+        idx_chunk = 0
+        try:
+            # print(await query.adapter.is_stream_output_supported())
+            is_stream = await query.adapter.is_stream_output_supported()
 
+        except AttributeError:
+            is_stream = False
+        if is_stream:
             for chunk in response:
                 if chunk.get('status_code') != 200:
                     raise DashscopeAPIError(
@@ -121,7 +128,43 @@ class DashScopeAPIRunner(runner.RequestRunner):
                     )
                 if not chunk:
                     continue
+                idx_chunk += 1
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                if stream_output.get('text') is not None:
+                    pending_content += stream_output.get('text')
+                # 是否是流式最后一个chunk
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True
 
+                # 获取模型传出的参考资料列表
+                references_dict_list = stream_output.get('doc_references', [])
+
+                # 从模型传出的参考资料信息中提取用于替换的字典
+                if references_dict_list is not None:
+                    for doc in references_dict_list:
+                        if doc.get('index_id') is not None:
+                            references_dict[doc.get('index_id')] = doc.get('doc_name')
+
+                    # 将参考资料替换到文本中
+                    pending_content = self._replace_references(pending_content, references_dict)
+
+                if idx_chunk % 64 == 0 or is_final:
+                    yield llm_entities.MessageChunk(
+                        role='assistant',
+                        content=pending_content,
+                        is_final=is_final,
+                    )
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')
+        else:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+                idx_chunk += 1
                 # 获取流式传输的output
                 stream_output = chunk.get('output', {})
                 if stream_output.get('text') is not None:
@@ -142,6 +185,8 @@ class DashScopeAPIRunner(runner.RequestRunner):
                 # 将参考资料替换到文本中
                 pending_content = self._replace_references(pending_content, references_dict)
 
+
+
             yield llm_entities.Message(
                 role='assistant',
                 content=pending_content,
@@ -177,6 +222,53 @@ class DashScopeAPIRunner(runner.RequestRunner):
         )
 
         # 处理API返回的流式输出
+        try:
+            # print(await query.adapter.is_stream_output_supported())
+            is_stream = await query.adapter.is_stream_output_supported()
+
+        except AttributeError:
+            is_stream = False
+        idx_chunk = 0
+        if is_stream:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+                idx_chunk += 1
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                if stream_output.get('text') is not None:
+                    pending_content += stream_output.get('text')
+
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True
+
+                # 获取模型传出的参考资料列表
+                references_dict_list = stream_output.get('doc_references', [])
+
+                # 从模型传出的参考资料信息中提取用于替换的字典
+                if references_dict_list is not None:
+                    for doc in references_dict_list:
+                        if doc.get('index_id') is not None:
+                            references_dict[doc.get('index_id')] = doc.get('doc_name')
+
+                    # 将参考资料替换到文本中
+                    pending_content = self._replace_references(pending_content, references_dict)
+                if is_final:
+                    yield llm_entities.MessageChunk(
+                        role='assistant',
+                        content=pending_content,
+                        is_final=is_final,
+
+                    )
+
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')
+
+
+        else:
             for chunk in response:
                 if chunk.get('status_code') != 200:
                     raise DashscopeAPIError(
@@ -190,6 +282,8 @@ class DashScopeAPIRunner(runner.RequestRunner):
                 if stream_output.get('text') is not None:
                     pending_content += stream_output.get('text')
 
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True
+
             # 保存当前会话的session_id用于下次对话的语境
             query.session.using_conversation.uuid = stream_output.get('session_id')
 

pkg/provider/runners/difysvapi.py

@@ -259,7 +259,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                     is_final = False
                     pending_agent_message += chunk['answer']
                 if is_stream:
-                    if batch_pending_index % 32 == 0 or is_final:
+                    if batch_pending_index % 64 == 0 or is_final:
                         yield llm_entities.MessageChunk(
                             role='assistant',
                             content=self._try_convert_thinking(pending_agent_message),