lint: add ruff rule

hugegraph-llm/src/hugegraph_llm/api/exceptions/rag_exceptions.py

@@ -21,9 +21,7 @@
 
 class ExternalException(HTTPException):
     def __init__(self):
-        super().__init__(
-            status_code=400, detail="Connect failed with error code -1, please check the input."
-        )
+        super().__init__(status_code=400, detail="Connect failed with error code -1, please check the input.")
 
 
 class ConnectionFailedException(HTTPException):

hugegraph-llm/src/hugegraph_llm/api/models/rag_requests.py

@@ -36,23 +36,13 @@ class RAGRequest(BaseModel):
     raw_answer: bool = Query(False, description="Use LLM to generate answer directly")
     vector_only: bool = Query(False, description="Use LLM to generate answer with vector")
     graph_only: bool = Query(True, description="Use LLM to generate answer with graph RAG only")
-    graph_vector_answer: bool = Query(
-        False, description="Use LLM to generate answer with vector & GraphRAG"
-    )
+    graph_vector_answer: bool = Query(False, description="Use LLM to generate answer with vector & GraphRAG")
     graph_ratio: float = Query(0.5, description="The ratio of GraphRAG ans & vector ans")
-    rerank_method: Literal["bleu", "reranker"] = Query(
-        "bleu", description="Method to rerank the results."
-    )
-    near_neighbor_first: bool = Query(
-        False, description="Prioritize near neighbors in the search results."
-    )
-    custom_priority_info: str = Query(
-        "", description="Custom information to prioritize certain results."
-    )
+    rerank_method: Literal["bleu", "reranker"] = Query("bleu", description="Method to rerank the results.")
+    near_neighbor_first: bool = Query(False, description="Prioritize near neighbors in the search results.")
+    custom_priority_info: str = Query("", description="Custom information to prioritize certain results.")
     # Graph Configs
-    max_graph_items: int = Query(
-        30, description="Maximum number of items for GQL queries in graph."
-    )
+    max_graph_items: int = Query(30, description="Maximum number of items for GQL queries in graph.")
     topk_return_results: int = Query(20, description="Number of sorted results to return finally.")
     vector_dis_threshold: float = Query(
         0.9,
@@ -64,14 +54,10 @@ class RAGRequest(BaseModel):
         description="TopK results returned for each keyword \
                                    extracted from the query, by default only the most similar one is returned.",
     )
-    client_config: Optional[GraphConfigRequest] = Query(
-        None, description="hugegraph server config."
-    )
+    client_config: Optional[GraphConfigRequest] = Query(None, description="hugegraph server config.")
 
     # Keep prompt params in the end
-    answer_prompt: Optional[str] = Query(
-        prompt.answer_prompt, description="Prompt to guide the answer generation."
-    )
+    answer_prompt: Optional[str] = Query(prompt.answer_prompt, description="Prompt to guide the answer generation.")
     keywords_extract_prompt: Optional[str] = Query(
         prompt.keywords_extract_prompt,
         description="Prompt for extracting keywords from query.",
@@ -87,9 +73,7 @@ class RAGRequest(BaseModel):
 class GraphRAGRequest(BaseModel):
     query: str = Query(..., description="Query you want to ask")
     # Graph Configs
-    max_graph_items: int = Query(
-        30, description="Maximum number of items for GQL queries in graph."
-    )
+    max_graph_items: int = Query(30, description="Maximum number of items for GQL queries in graph.")
     topk_return_results: int = Query(20, description="Number of sorted results to return finally.")
     vector_dis_threshold: float = Query(
         0.9,
@@ -102,24 +86,16 @@ class GraphRAGRequest(BaseModel):
                                     from the query, by default only the most similar one is returned.",
     )
 
-    client_config: Optional[GraphConfigRequest] = Query(
-        None, description="hugegraph server config."
-    )
+    client_config: Optional[GraphConfigRequest] = Query(None, description="hugegraph server config.")
     get_vertex_only: bool = Query(False, description="return only keywords & vertex (early stop).")
 
     gremlin_tmpl_num: int = Query(
         1,
         description="Number of Gremlin templates to use. If num <=0 means template is not provided",
     )
-    rerank_method: Literal["bleu", "reranker"] = Query(
-        "bleu", description="Method to rerank the results."
-    )
-    near_neighbor_first: bool = Query(
-        False, description="Prioritize near neighbors in the search results."
-    )
-    custom_priority_info: str = Query(
-        "", description="Custom information to prioritize certain results."
-    )
+    rerank_method: Literal["bleu", "reranker"] = Query("bleu", description="Method to rerank the results.")
+    near_neighbor_first: bool = Query(False, description="Prioritize near neighbors in the search results.")
+    custom_priority_info: str = Query("", description="Custom information to prioritize certain results.")
     gremlin_prompt: Optional[str] = Query(
         prompt.gremlin_generate_prompt,
         description="Prompt for the Text2Gremlin query.",
@@ -163,16 +139,12 @@ class GremlinOutputType(str, Enum):
 
 class GremlinGenerateRequest(BaseModel):
     query: str
-    example_num: Optional[int] = Query(
-        0, description="Number of Gremlin templates to use.(0 means no templates)"
-    )
+    example_num: Optional[int] = Query(0, description="Number of Gremlin templates to use.(0 means no templates)")
     gremlin_prompt: Optional[str] = Query(
         prompt.gremlin_generate_prompt,
         description="Prompt for the Text2Gremlin query.",
     )
-    client_config: Optional[GraphConfigRequest] = Query(
-        None, description="hugegraph server config."
-    )
+    client_config: Optional[GraphConfigRequest] = Query(None, description="hugegraph server config.")
     output_types: Optional[List[GremlinOutputType]] = Query(
         default=[GremlinOutputType.TEMPLATE_GREMLIN],
         description="""
@@ -189,7 +161,5 @@ def validate_prompt_placeholders(cls, v):
             required_placeholders = ["{query}", "{schema}", "{example}", "{vertices}"]
             missing = [p for p in required_placeholders if p not in v]
             if missing:
-                raise ValueError(
-                    f"Prompt template is missing required placeholders: {', '.join(missing)}"
-                )
+                raise ValueError(f"Prompt template is missing required placeholders: {', '.join(missing)}")
         return v

hugegraph-llm/src/hugegraph_llm/api/rag_api.py

@@ -74,8 +74,7 @@ def rag_answer_api(req: RAGRequest):
             # Keep prompt params in the end
             custom_related_information=req.custom_priority_info,
             answer_prompt=req.answer_prompt or prompt.answer_prompt,
-            keywords_extract_prompt=req.keywords_extract_prompt
-            or prompt.keywords_extract_prompt,
+            keywords_extract_prompt=req.keywords_extract_prompt or prompt.keywords_extract_prompt,
             gremlin_prompt=req.gremlin_prompt or prompt.gremlin_generate_prompt,
         )
         # TODO: we need more info in the response for users to understand the query logic
@@ -146,9 +145,7 @@ def graph_rag_recall_api(req: GraphRAGRequest):
 
         except TypeError as e:
             log.error("TypeError in graph_rag_recall_api: %s", e)
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST, detail=str(e)
-            ) from e
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e)) from e
         except Exception as e:
             log.error("Unexpected error occurred: %s", e)
             raise HTTPException(
@@ -159,9 +156,7 @@ def graph_rag_recall_api(req: GraphRAGRequest):
     @router.post("/config/graph", status_code=status.HTTP_201_CREATED)
     def graph_config_api(req: GraphConfigRequest):
         # Accept status code
-        res = apply_graph_conf(
-            req.url, req.name, req.user, req.pwd, req.gs, origin_call="http"
-        )
+        res = apply_graph_conf(req.url, req.name, req.user, req.pwd, req.gs, origin_call="http")
         return generate_response(RAGResponse(status_code=res, message="Missing Value"))
 
     # TODO: restructure the implement of llm to three types, like "/config/chat_llm"
@@ -178,37 +173,27 @@ def llm_config_api(req: LLMConfigRequest):
                 origin_call="http",
             )
         else:
-            res = apply_llm_conf(
-                req.host, req.port, req.language_model, None, origin_call="http"
-            )
+            res = apply_llm_conf(req.host, req.port, req.language_model, None, origin_call="http")
         return generate_response(RAGResponse(status_code=res, message="Missing Value"))
 
     @router.post("/config/embedding", status_code=status.HTTP_201_CREATED)
     def embedding_config_api(req: LLMConfigRequest):
         llm_settings.embedding_type = req.llm_type
 
         if req.llm_type == "openai":
-            res = apply_embedding_conf(
-                req.api_key, req.api_base, req.language_model, origin_call="http"
-            )
+            res = apply_embedding_conf(req.api_key, req.api_base, req.language_model, origin_call="http")
         else:
-            res = apply_embedding_conf(
-                req.host, req.port, req.language_model, origin_call="http"
-            )
+            res = apply_embedding_conf(req.host, req.port, req.language_model, origin_call="http")
         return generate_response(RAGResponse(status_code=res, message="Missing Value"))
 
     @router.post("/config/rerank", status_code=status.HTTP_201_CREATED)
     def rerank_config_api(req: RerankerConfigRequest):
         llm_settings.reranker_type = req.reranker_type
 
         if req.reranker_type == "cohere":
-            res = apply_reranker_conf(
-                req.api_key, req.reranker_model, req.cohere_base_url, origin_call="http"
-            )
+            res = apply_reranker_conf(req.api_key, req.reranker_model, req.cohere_base_url, origin_call="http")
         elif req.reranker_type == "siliconflow":
-            res = apply_reranker_conf(
-                req.api_key, req.reranker_model, None, origin_call="http"
-            )
+            res = apply_reranker_conf(req.api_key, req.reranker_model, None, origin_call="http")
         else:
             res = status.HTTP_501_NOT_IMPLEMENTED
         return generate_response(RAGResponse(status_code=res, message="Missing Value"))

hugegraph-llm/src/hugegraph_llm/config/generate.py

@@ -28,9 +28,7 @@
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Generate hugegraph-llm config file")
-    parser.add_argument(
-        "-U", "--update", default=True, action="store_true", help="Update the config file"
-    )
+    parser.add_argument("-U", "--update", default=True, action="store_true", help="Update the config file")
     args = parser.parse_args()
     if args.update:
         huge_settings.generate_env()

hugegraph-llm/src/hugegraph_llm/config/index_config.py

@@ -26,9 +26,7 @@ class IndexConfig(BaseConfig):
 
     qdrant_host: Optional[str] = os.environ.get("QDRANT_HOST", None)
     qdrant_port: int = int(os.environ.get("QDRANT_PORT", "6333"))
-    qdrant_api_key: Optional[str] = (
-        os.environ.get("QDRANT_API_KEY") if os.environ.get("QDRANT_API_KEY") else None
-    )
+    qdrant_api_key: Optional[str] = os.environ.get("QDRANT_API_KEY") if os.environ.get("QDRANT_API_KEY") else None
 
     milvus_host: Optional[str] = os.environ.get("MILVUS_HOST", None)
     milvus_port: int = int(os.environ.get("MILVUS_PORT", "19530"))

hugegraph-llm/src/hugegraph_llm/config/llm_config.py

@@ -36,33 +36,23 @@ class LLMConfig(BaseConfig):
     hybrid_llm_weights: Optional[float] = 0.5
     # TODO: divide RAG part if necessary
     # 1. OpenAI settings
-    openai_chat_api_base: Optional[str] = os.environ.get(
-        "OPENAI_BASE_URL", "https://api.openai.com/v1"
-    )
+    openai_chat_api_base: Optional[str] = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1")
     openai_chat_api_key: Optional[str] = os.environ.get("OPENAI_API_KEY")
     openai_chat_language_model: Optional[str] = "gpt-4.1-mini"
-    openai_extract_api_base: Optional[str] = os.environ.get(
-        "OPENAI_BASE_URL", "https://api.openai.com/v1"
-    )
+    openai_extract_api_base: Optional[str] = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1")
     openai_extract_api_key: Optional[str] = os.environ.get("OPENAI_API_KEY")
     openai_extract_language_model: Optional[str] = "gpt-4.1-mini"
-    openai_text2gql_api_base: Optional[str] = os.environ.get(
-        "OPENAI_BASE_URL", "https://api.openai.com/v1"
-    )
+    openai_text2gql_api_base: Optional[str] = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1")
     openai_text2gql_api_key: Optional[str] = os.environ.get("OPENAI_API_KEY")
     openai_text2gql_language_model: Optional[str] = "gpt-4.1-mini"
-    openai_embedding_api_base: Optional[str] = os.environ.get(
-        "OPENAI_EMBEDDING_BASE_URL", "https://api.openai.com/v1"
-    )
+    openai_embedding_api_base: Optional[str] = os.environ.get("OPENAI_EMBEDDING_BASE_URL", "https://api.openai.com/v1")
     openai_embedding_api_key: Optional[str] = os.environ.get("OPENAI_EMBEDDING_API_KEY")
     openai_embedding_model: Optional[str] = "text-embedding-3-small"
     openai_chat_tokens: int = 8192
     openai_extract_tokens: int = 256
     openai_text2gql_tokens: int = 4096
     # 2. Rerank settings
-    cohere_base_url: Optional[str] = os.environ.get(
-        "CO_API_URL", "https://api.cohere.com/v1/rerank"
-    )
+    cohere_base_url: Optional[str] = os.environ.get("CO_API_URL", "https://api.cohere.com/v1/rerank")
     reranker_api_key: Optional[str] = None
     reranker_model: Optional[str] = None
     # 3. Ollama settings

hugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.py

@@ -107,7 +107,6 @@ def ensure_yaml_file_exists(self):
             log.info("Prompt file '%s' doesn't exist, create it.", yaml_file_path)
 
     def save_to_yaml(self):
-
         def to_literal(val):
             return LiteralStr(val) if isinstance(val, str) else val
 

hugegraph-llm/src/hugegraph_llm/demo/rag_demo/admin_block.py

@@ -108,9 +108,7 @@ def create_admin_block():
         )
 
         # Error message box, initially hidden
-        error_message = gr.Textbox(
-            label="", visible=False, interactive=False, elem_classes="error-message"
-        )
+        error_message = gr.Textbox(label="", visible=False, interactive=False, elem_classes="error-message")
 
         # Button to submit password
         submit_button = gr.Button("Submit")

hugegraph-llm/src/hugegraph_llm/demo/rag_demo/app.py

@@ -94,20 +94,16 @@ def init_rag_ui() -> gr.Interface:
         textbox_array_graph_config = create_configs_block()
 
         with gr.Tab(label="1. Build RAG Index 💡"):
-            textbox_input_text, textbox_input_schema, textbox_info_extract_template = (
-                create_vector_graph_block()
-            )
+            textbox_input_text, textbox_input_schema, textbox_info_extract_template = create_vector_graph_block()
         with gr.Tab(label="2. (Graph)RAG & User Functions 📖"):
             (
                 textbox_inp,
                 textbox_answer_prompt_input,
                 textbox_keywords_extract_prompt_input,
-                textbox_custom_related_information
+                textbox_custom_related_information,
             ) = create_rag_block()
         with gr.Tab(label="3. Text2gremlin ⚙️"):
-            textbox_gremlin_inp, textbox_gremlin_schema, textbox_gremlin_prompt = (
-                create_text2gremlin_block()
-            )
+            textbox_gremlin_inp, textbox_gremlin_schema, textbox_gremlin_prompt = create_text2gremlin_block()
         with gr.Tab(label="4. Graph Tools 🚧"):
             create_other_block()
         with gr.Tab(label="5. Admin Tools 🛠"):