[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Signed-off-by: Dong, Bo1 <[email protected]>

comps/reranks/neural-speed/neuralspeed-docker/server.py

@@ -28,6 +28,7 @@ class Request(Struct, kw_only=True):
     query: str
     docs: List[str]
 
+
 class Response(Struct, kw_only=True):
     scores: List[float]
 
@@ -45,17 +46,17 @@ def __init__(self):
             n_ctx=INFERENCE_CONTEXT + 2,
         )
 
-    def forward(self, datas: List[Request]) -> List[Response]:
-        batch = len(datas)
+    def forward(self, data: List[Request]) -> List[Response]:
+        batch = len(data)
         ndoc = []
         inps = []
-        for data in datas:
+        for data in data:
             inp = [[data.query, doc] for doc in data.docs]
             inps.extend(inp)
             ndoc.append(len(data.docs))
-        outs=[]
-        for i in range(0,len(inps),INFERENCE_BATCH_SIZE):
-            inp_bs = inps[i:i+INFERENCE_BATCH_SIZE]
+        outs = []
+        for i in range(0, len(inps), INFERENCE_BATCH_SIZE):
+            inp_bs = inps[i : i + INFERENCE_BATCH_SIZE]
             inputs = self.tokenizer(
                 inp_bs, padding=True, truncation=True, max_length=INFERENCE_CONTEXT, return_tensors="pt"
             )
@@ -67,14 +68,14 @@ def forward(self, datas: List[Request]) -> List[Response]:
                 continuous_batching=False,
                 ignore_padding=True,
             )
-            logger.info(f'Toal batch {batch} input shape {inputs.input_ids.shape} time {time.time()-st}')
+            logger.info(f"Toal batch {batch} input shape {inputs.input_ids.shape} time {time.time()-st}")
             outs.append(output)
-        ns_outputs=numpy.concatenate(outs,axis=0)
-        resps =[]
+        ns_outputs = numpy.concatenate(outs, axis=0)
+        resps = []
         pos = 0
         for i in range(batch):
-            resp = Response(scores=ns_outputs[pos:pos+ndoc[i]].tolist())
-            pos+=ndoc[i]
+            resp = Response(scores=ns_outputs[pos : pos + ndoc[i]].tolist())
+            pos += ndoc[i]
             resps.append(resp)
         return resps
 

comps/reranks/neural-speed/reranking_neuralspeed_svc.py

@@ -22,7 +22,6 @@
     statistics_dict,
 )
 
-
 # class MosecEmbeddings(OpenAIEmbeddings):
 
 #     def _get_len_safe_embeddings(
@@ -67,8 +66,7 @@ def reranking(input: SearchedDoc) -> LLMParamsDoc:
         url = mosec_reranking_endpoint + "/inference"
         data = {"query": input.initial_query, "texts": docs}
         resp = requests.post(url, data=msgspec.msgpack.encode(data))
-        response = msgspec.msgpack.decode(resp.content)['scores']
-
+        response = msgspec.msgpack.decode(resp.content)["scores"]
 
         response_data = response.json()
         best_response = max(response_data, key=lambda response: response["score"])
@@ -90,7 +88,7 @@ def reranking(input: SearchedDoc) -> LLMParamsDoc:
         if logflag:
             logger.info(input.initial_query)
         return LLMParamsDoc(query=input.initial_query)
-    
+
 
 if __name__ == "__main__":
     mosec_reranking_endpoint = os.getenv("MOSEC_RERANKING_ENDPOINT", "http://localhost:6001")