实现terminalcode和文件交互

llm_server/test_asr.py

@@ -12,6 +12,8 @@ import requests
 import argparse
 import os
 import sys
+import base64
+import mimetypes
 
 DEFAULT_URL = "http://127.0.0.1:8901/v1/chat/completions"
 
@@ -33,12 +35,24 @@ def get_audio_duration_sec(file_path: str) -> float:
             return -1.0
 
 # ----------------------------------------------------------------------
-def file_to_url(file_path: str) -> str:
-    """Convert local file path to a file:// URL accepted by vLLM."""
-    abs_path = os.path.abspath(file_path)
-    return "file://" + abs_path.replace("\\", "/")
+def file_to_url(file_path: str, use_base64: bool = False) -> str:
+    """Convert local file path to a URL accepted by vLLM.
+    
+    When the server is remote, use base64 data URL instead of file://
+    since the remote server cannot access local filesystem paths.
+    """
+    if use_base64:
+        mime_type, _ = mimetypes.guess_type(file_path)
+        if mime_type is None:
+            mime_type = "audio/wav"
+        with open(file_path, "rb") as f:
+            b64_data = base64.b64encode(f.read()).decode("utf-8")
+        return f"data:{mime_type};base64,{b64_data}"
+    else:
+        abs_path = os.path.abspath(file_path)
+        return "file://" + abs_path.replace("\\", "/")
 
-def caption_audio(audio_path: str, server_url: str = DEFAULT_URL) -> str:
+def caption_audio(audio_path: str, server_url: str = DEFAULT_URL, use_base64: bool = False) -> str:
     """
     Send audio to the Qwen3-Omni-30B-A3B-Captioner and return its description.
     """
@@ -54,7 +68,7 @@ def caption_audio(audio_path: str, server_url: str = DEFAULT_URL) -> str:
             file=sys.stderr
         )
 
-    audio_url = file_to_url(audio_path)
+    audio_url = file_to_url(audio_path, use_base64=use_base64)
 
     # The model expects NO text prompt. Only the audio input is required.
     payload = {
@@ -95,14 +109,17 @@ def main():
                         help="Output text file (if not provided, print to stdout)")
     parser.add_argument("--verbose", "-v", action="store_true",
                         help="Print detailed request/response info")
+    parser.add_argument("--base64", "-b", action="store_true",
+                        help="Send audio as base64 data URL (use when server is remote)")
 
     args = parser.parse_args()
 
     if args.verbose:
         print(f"Audio file: {args.audio}")
         print(f"Server URL: {args.url}")
+        print(f"Base64 mode: {args.base64}")
 
-    caption_text = caption_audio(args.audio, args.url)
+    caption_text = caption_audio(args.audio, args.url, use_base64=args.base64)
 
     if args.output:
         with open(args.output, "w", encoding="utf-8") as f: