Format Benchmark Code (#399)

benchmark/generative_agents/bench_other.py

@@ -1,29 +1,29 @@
 import argparse
-from functools import partial
 import json
 import time
+from functools import partial
 from pathlib import Path
 
+from agent_functions import (
+    action_location_object_prompt,
+    action_location_sector_prompt,
+    generate_event_triple_prompt,
+    generate_pronunciatio_prompt,
+    poignancy_event_prompt,
+)
 from tqdm import tqdm
+
 from sglang.test.test_utils import (
     add_common_other_args_and_parse,
     call_generate_lightllm,
-    call_generate_vllm,
     call_generate_srt_raw,
+    call_generate_vllm,
 )
-from sglang.utils import read_jsonl, dump_state_text
-
-from agent_functions import (
-    poignancy_event_prompt,
-    generate_event_triple_prompt,
-    generate_pronunciatio_prompt,
-    action_location_sector_prompt,
-    action_location_object_prompt,
-)
+from sglang.utils import dump_state_text, read_jsonl
 
 
 def main(args):
-    lines = read_jsonl(args.data_path)[:args.num_events]
+    lines = read_jsonl(args.data_path)[: args.num_events]
     mapping = {
         "poignancy_event": poignancy_event_prompt,
         "generate_event_triple": generate_event_triple_prompt,
@@ -46,7 +46,7 @@ def main(args):
         url = f"{args.host}:{args.port}/generate"
         call_generate = partial(call_generate_srt_raw, url=url)
     elif args.backend == "guidance":
-        from guidance import models, gen
+        from guidance import gen, models
 
         model = models.LlamaCpp(
             str(Path.home()) + "/model_weights/Llama-2-7b-chat.gguf",
@@ -55,11 +55,15 @@ def main(args):
         )
 
         def call_generate(prompt, temperature, max_tokens, stop):
-            out = model + prompt + gen(
-                name="result",
-                max_tokens=max_tokens,
-                temperature=temperature,
-                stop=stop,
+            out = (
+                model
+                + prompt
+                + gen(
+                    name="result",
+                    max_tokens=max_tokens,
+                    temperature=temperature,
+                    stop=stop,
+                )
             )
             return out["result"]
 
@@ -87,7 +91,7 @@ def main(args):
             "backend": args.backend,
             "num_gpus": 1,
             "latency": round(latency, 3),
-            # to pack weighted functions as a single agent            
+            # to pack weighted functions as a single agent
             "num_requests": len(arguments) / len(mapping),
             "other": {
                 "parallel": args.parallel,