Fix: support cross language for API. (#8946)

### What problem does this PR solve?

Close #8943

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/apps/sdk/doc.py

 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
-from rag.prompts import keyword_extraction
+from rag.prompts import keyword_extraction, cross_languages
 from rag.utils import rmSpace
 from rag.utils.storage_factory import STORAGE_IMPL
 
     question = req["question"]
     doc_ids = req.get("document_ids", [])
     use_kg = req.get("use_kg", False)
+    langs = req.get("cross_languages", [])
     if not isinstance(doc_ids, list):
         return get_error_data_result("`documents` should be a list")
     doc_ids_list = KnowledgebaseService.list_documents_by_ids(kb_ids)
         if req.get("rerank_id"):
             rerank_mdl = LLMBundle(kb.tenant_id, LLMType.RERANK, llm_name=req["rerank_id"])
 
+        if langs:
+            question = cross_languages(kb.tenant_id, None, question, langs)
+
         if req.get("keyword", False):
             chat_mdl = LLMBundle(kb.tenant_id, LLMType.CHAT)
             question += keyword_extraction(chat_mdl, question)

docs/references/http_api_reference.md

   - `"rerank_id"`: `string`  
   - `"keyword"`: `boolean`  
   - `"highlight"`: `boolean`
+  - `"cross_languages"`: `list[string]`  
 
 ##### Request example
 
   Specifies whether to enable highlighting of matched terms in the results:  
   - `true`: Enable highlighting of matched terms.
   - `false`: Disable highlighting of matched terms (default).
+- `"cross_languages"`: (*Body parameter*) `list[string]`  
+  The languages that should be translated into, in order to achieve keywords retrievals in different languages.
 
 #### Response
 

docs/references/python_api_reference.md

 - `True`: Enable highlighting of matched terms.
 - `False`: Disable highlighting of matched terms (default).
 
+##### cross_languages:  `list[string]`  
+
+The languages that should be translated into, in order to achieve keywords retrievals in different languages.
+
 #### Returns
 
 - Success: A list of `Chunk` objects representing the document chunks.

graphrag/general/extractor.py

         use_prompt = prompt_template.format(**context_base)
         logging.info(f"Trigger summary: {entity_or_relation_name}")
         async with chat_limiter:
-            summary = await trio.to_thread.run_sync(lambda: self._chat(use_prompt, [{"role": "user", "content": "Output: "}], {"temperature": 0.8}))
+            summary = await trio.to_thread.run_sync(lambda: self._chat(use_prompt, [{"role": "user", "content": "Output: "}]))
         return summary

graphrag/general/graph_extractor.py

             history.append({"role": "assistant", "content": response})
             history.append({"role": "user", "content": LOOP_PROMPT})
             async with chat_limiter:
-                continuation = await trio.to_thread.run_sync(lambda: self._chat("", history, {"temperature": 0.8}))
+                continuation = await trio.to_thread.run_sync(lambda: self._chat("", history))
             token_count += num_tokens_from_string("\n".join([m["content"] for m in history]) + response)
             if continuation != "Y":
                 break

graphrag/light/graph_extractor.py

             **self._context_base, input_text="{input_text}"
         ).format(**self._context_base, input_text=content)
 
-        gen_conf = {"temperature": 0.8}
+        gen_conf = {}
         async with chat_limiter:
             final_result = await trio.to_thread.run_sync(lambda: self._chat(hint_prompt, [{"role": "user", "content": "Output:"}], gen_conf))
         token_count += num_tokens_from_string(hint_prompt + final_result)

sdk/python/ragflow_sdk/ragflow.py

         top_k=1024,
         rerank_id: str | None = None,
         keyword: bool = False,
+        cross_languages: list[str]|None = None
     ):
         if document_ids is None:
             document_ids = []
             "question": question,
             "dataset_ids": dataset_ids,
             "document_ids": document_ids,
+            "cross_languages": cross_languages
         }
         # Send a POST request to the backend service (using requests library as an example, actual implementation may vary)
         res = self.post("/retrieval", json=data_json)