v0.21.1-fastapi

sdk/python/ragflow_sdk/modules/dataset.py

@@ -100,12 +100,51 @@ class DataSet(Base):
         res = res.json()
         if res.get("code") != 0:
             raise Exception(res["message"])
-
+        
+    
+    def _get_documents_status(self, document_ids):
+        import time
+        terminal_states = {"DONE", "FAIL", "CANCEL"}
+        interval_sec = 1
+        pending = set(document_ids)
+        finished = []
+        while pending:
+            for doc_id in list(pending):
+                def fetch_doc(doc_id: str) -> Document | None:
+                    try:
+                        docs = self.list_documents(id=doc_id)
+                        return docs[0] if docs else None
+                    except Exception:
+                        return None
+                doc = fetch_doc(doc_id)
+                if doc is None:
+                    continue
+                if isinstance(doc.run, str) and doc.run.upper() in terminal_states:
+                    finished.append((doc_id, doc.run, doc.chunk_count, doc.token_count))
+                    pending.discard(doc_id)
+                elif float(doc.progress or 0.0) >= 1.0:
+                    finished.append((doc_id, "DONE", doc.chunk_count, doc.token_count))
+                    pending.discard(doc_id)
+            if pending:
+                time.sleep(interval_sec)
+        return finished
+    
     def async_parse_documents(self, document_ids):
         res = self.post(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})
         res = res.json()
         if res.get("code") != 0:
             raise Exception(res.get("message"))
+        
+
+    def parse_documents(self, document_ids):
+        try:
+            self.async_parse_documents(document_ids)
+            self._get_documents_status(document_ids)
+        except KeyboardInterrupt:
+            self.async_cancel_parse_documents(document_ids)
+            
+        return self._get_documents_status(document_ids)
+
 
     def async_cancel_parse_documents(self, document_ids):
         res = self.rm(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})

sdk/python/ragflow_sdk/modules/session.py

@@ -33,35 +33,52 @@ class Session(Base):
                 self.__session_type = "agent"
         super().__init__(rag, res_dict)
 
-    def ask(self, question="", stream=True, **kwargs):
+
+    def ask(self, question="", stream=False, **kwargs):
+        """
+        Ask a question to the session. If stream=True, yields Message objects as they arrive (SSE streaming).
+        If stream=False, returns a single Message object for the final answer.
+        """
         if self.__session_type == "agent":
             res = self._ask_agent(question, stream)
         elif self.__session_type == "chat":
             res = self._ask_chat(question, stream, **kwargs)
+        else:
+            raise Exception(f"Unknown session type: {self.__session_type}")
 
         if stream:
-            for line in res.iter_lines():
-                line = line.decode("utf-8")
-                if line.startswith("{"):
-                    json_data = json.loads(line)
-                    raise Exception(json_data["message"])
-                if not line.startswith("data:"):
-                    continue
-                json_data = json.loads(line[5:])
-                if json_data["data"] is True or json_data["data"].get("running_status"):
-                    continue
-                message = self._structure_answer(json_data)
-                yield message
+            for line in res.iter_lines(decode_unicode=True):
+                if not line:
+                    continue  # Skip empty lines
+                line = line.strip()
+
+                if line.startswith("data:"):
+                    content = line[len("data:"):].strip()
+                    if content == "[DONE]":
+                        break  # End of stream
+                else:
+                    content = line
+
+                try:
+                    json_data = json.loads(content)
+                except json.JSONDecodeError:
+                    continue  # Skip lines that are not valid JSON
+
+                event = json_data.get("event")
+                if event == "message":
+                    yield self._structure_answer(json_data)
+                elif event == "message_end":
+                    return  # End of message stream
         else:
             try:
-                json_data = json.loads(res.text)
+                json_data = res.json()
             except ValueError:
                 raise Exception(f"Invalid response {res}")
-            return self._structure_answer(json_data)
+            yield self._structure_answer(json_data["data"])
         
 
     def _structure_answer(self, json_data):
-        answer = json_data["data"]["answer"]
+        answer = json_data["data"]["content"]
         reference = json_data["data"].get("reference", {})
         temp_dict = {
             "content": answer,