Fix: Update poetry.lock to include httpx dependency for proxy service support

poetry.lock

@@ -18,7 +18,7 @@ version = "3.7.1"
 description = "High level compatibility layer for multiple asynchronous event loop implementations"
 optional = false
 python-versions = ">=3.7"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "anyio-3.7.1-py3-none-any.whl", hash = "sha256:91dee416e570e92c64041bd18b900d1d6fa78dff7048769ce5ac5ddad004fbb5"},
     {file = "anyio-3.7.1.tar.gz", hash = "sha256:44a3c9aba0f5defa43261a8b3efb97891f2bd7d804e0e1f56419befa1adfc780"},
@@ -156,7 +156,7 @@ version = "2025.8.3"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.7"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "certifi-2025.8.3-py3-none-any.whl", hash = "sha256:f6c12493cfb1b06ba2ff328595af9350c65d6644968e5d3a2ffd78699af217a5"},
     {file = "certifi-2025.8.3.tar.gz", hash = "sha256:e564105f78ded564e3ae7c923924435e1daa7463faeab5bb932bc53ffae63407"},
@@ -630,7 +630,7 @@ version = "0.16.0"
 description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86"},
     {file = "h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1"},
@@ -678,7 +678,7 @@ version = "1.0.9"
 description = "A minimal low-level HTTP client."
 optional = false
 python-versions = ">=3.8"
-groups = ["dev"]
+groups = ["main"]
 files = [
     {file = "httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55"},
     {file = "httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8"},
@@ -756,7 +756,7 @@ version = "0.25.2"
 description = "The next generation HTTP client."
 optional = false
 python-versions = ">=3.8"
-groups = ["dev"]
+groups = ["main"]
 files = [
     {file = "httpx-0.25.2-py3-none-any.whl", hash = "sha256:a05d3d052d9b2dfce0e3896636467f8a5342fb2b902c819428e1ac65413ca118"},
     {file = "httpx-0.25.2.tar.gz", hash = "sha256:8b8fcaa0c8ea7b05edd69a094e63a2094c4efcb48129fb757361bc423c0ad9e8"},
@@ -835,7 +835,7 @@ version = "3.10"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.6"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
     {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
@@ -2443,7 +2443,7 @@ version = "1.3.1"
 description = "Sniff out which async library your code is running under"
 optional = false
 python-versions = ">=3.7"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
     {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
@@ -3206,4 +3206,4 @@ test = ["pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.11"
-content-hash = "ebb16163670f970e4d506a8230fbb256edc8d5a749255bbbc9dc9cd17fc870eb"
+content-hash = "7ca1372ab8050eedee965f5b1059f004ace52d36c44c0f6f00e042a4d5a0b35e"

test_endpoints.py

@@ -0,0 +1,377 @@
+"""
+Test file for Multi-Utility Server endpoints.
+Test both Subtitles and Embeddings APIs with the deployed server.
+
+Usage:
+    python test_endpoints.py
+
+Modify the test data in the TEST_DATA section to test different inputs.
+"""
+
+import json
+import os
+from pathlib import Path
+from typing import Any, Dict, List
+
+import requests
+
+# ============================================================================
+# CONFIGURATION
+# ============================================================================
+
+BASE_URL = "https://abhisheksan-multiutility-server.hf.space"
+API_KEY = "zL6Rod5869J0"  # Replace with your actual API key
+
+# ============================================================================
+# TEST DATA - MODIFY THESE TO TEST DIFFERENT INPUTS
+# ============================================================================
+
+# Test data for Subtitles API
+SUBTITLE_TEST_DATA = {
+    "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
+    "lang": "en",
+}
+
+# Test data for Embeddings API
+EMBEDDING_TEST_DATA = {
+    "texts": [
+        "Hello, how are you?",
+        "Machine learning is fascinating",
+        "Python is a great programming language",
+    ],
+    "normalize": True,
+}
+
+# ============================================================================
+# HELPER FUNCTIONS
+# ============================================================================
+
+
+def print_section(title: str):
+    """Print a formatted section header."""
+    print("\n" + "=" * 80)
+    print(f"  {title}")
+    print("=" * 80 + "\n")
+
+
+def print_response(response: requests.Response):
+    """Print formatted response details."""
+    print(f"Status Code: {response.status_code}")
+    print(f"Response Time: {response.elapsed.total_seconds():.2f}s")
+    print("\nResponse Headers:")
+    for key, value in response.headers.items():
+        print(f"  {key}: {value}")
+    print("\nResponse Body:")
+    try:
+        print(json.dumps(response.json(), indent=2))
+    except Exception:
+        print(response.text)
+
+
+def make_request(
+    method: str,
+    endpoint: str,
+    data: Dict[str, Any] = None,
+    headers: Dict[str, str] = None,
+) -> requests.Response:
+    """Make HTTP request to the API."""
+    url = f"{BASE_URL}{endpoint}"
+    default_headers = {"Content-Type": "application/json", "X-API-Key": API_KEY}
+
+    if headers:
+        default_headers.update(headers)
+
+    try:
+        if method.upper() == "GET":
+            response = requests.get(url, headers=default_headers)
+        elif method.upper() == "POST":
+            response = requests.post(url, json=data, headers=default_headers)
+        else:
+            raise ValueError(f"Unsupported HTTP method: {method}")
+
+        return response
+    except requests.exceptions.RequestException as e:
+        print(f"❌ Request failed: {str(e)}")
+        raise
+
+
+# ============================================================================
+# TEST FUNCTIONS
+# ============================================================================
+
+
+def test_health_check():
+    """Test the main health check endpoint."""
+    print_section("TEST: Health Check")
+
+    try:
+        response = make_request("GET", "/health")
+        print_response(response)
+
+        if response.status_code == 200:
+            print("\n✅ Health check passed!")
+        else:
+            print("\n❌ Health check failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_root_endpoint():
+    """Test the root endpoint."""
+    print_section("TEST: Root Endpoint")
+
+    try:
+        response = make_request("GET", "/")
+        print_response(response)
+
+        if response.status_code == 200:
+            print("\n✅ Root endpoint test passed!")
+        else:
+            print("\n❌ Root endpoint test failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_subtitles_health():
+    """Test the subtitles service health check."""
+    print_section("TEST: Subtitles Health Check")
+
+    try:
+        response = make_request("GET", "/api/v1/subtitles/health")
+        print_response(response)
+
+        if response.status_code == 200:
+            print("\n✅ Subtitles health check passed!")
+        else:
+            print("\n❌ Subtitles health check failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_audio_transcription():
+    """Test the audio file transcription endpoint."""
+    print_section("TEST: Audio File Transcription")
+
+    # Create a small test audio file (silent WAV)
+    # This is a minimal WAV file header for a 1-second silent audio
+    print("Creating test audio file...")
+    test_audio = b"RIFF$\x00\x00\x00WAVEfmt \x10\x00\x00\x00\x01\x00\x01\x00D\xac\x00\x00\x88X\x01\x00\x02\x00\x10\x00data\x00\x00\x00\x00"
+
+    test_file_path = "test_audio.wav"
+
+    try:
+        # Write test audio file
+        with open(test_file_path, "wb") as f:
+            f.write(test_audio)
+
+        print(f"Test file created: {test_file_path}")
+        print("Note: Using minimal WAV file for testing\n")
+
+        # Make request with file upload
+        url = f"{BASE_URL}/api/v1/subtitles/transcribe"
+        headers = {"X-API-Key": API_KEY}
+
+        with open(test_file_path, "rb") as f:
+            files = {"file": ("test_audio.wav", f, "audio/wav")}
+            data = {"lang": "en"}
+
+            response = requests.post(url, headers=headers, files=files, data=data)
+
+        print_response(response)
+
+        if response.status_code == 200:
+            data = response.json()
+            transcription_count = len(data.get("transcription", []))
+            print(f"\n✅ Audio transcription passed!")
+            print(f"   - Language: {data.get('language')}")
+            print(f"   - File name: {data.get('file_name')}")
+            print(f"   - Number of segments: {transcription_count}")
+
+            # Print transcription segments
+            if transcription_count > 0:
+                print(f"\n   Transcription segments:")
+                for i, line in enumerate(data.get("transcription", [])[:5]):
+                    print(f"     {i + 1}. {line}")
+            else:
+                print("   (No transcription - test audio is silent)")
+        else:
+            print("\n❌ Audio transcription failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+    finally:
+        # Cleanup test file
+        if os.path.exists(test_file_path):
+            os.remove(test_file_path)
+            print(f"\n   Cleaned up test file: {test_file_path}")
+
+
+def test_subtitles_extract():
+    """Test the subtitles extraction endpoint."""
+    print_section("TEST: Extract Subtitles")
+
+    print("Test Data:")
+    print(json.dumps(SUBTITLE_TEST_DATA, indent=2))
+    print()
+
+    try:
+        response = make_request(
+            "POST", "/api/v1/subtitles/extract", data=SUBTITLE_TEST_DATA
+        )
+        print_response(response)
+
+        if response.status_code == 200:
+            data = response.json()
+            subtitle_count = len(data.get("subtitles", []))
+            print(f"\n✅ Subtitles extraction passed!")
+            print(f"   - Video ID: {data.get('video_id')}")
+            print(f"   - Language: {data.get('language')}")
+            print(f"   - Number of subtitle lines: {subtitle_count}")
+
+            # Print first few subtitle lines
+            if subtitle_count > 0:
+                print(f"\n   First 5 subtitle lines:")
+                for i, line in enumerate(data.get("subtitles", [])[:5]):
+                    print(f"     {i + 1}. {line}")
+        else:
+            print("\n❌ Subtitles extraction failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_embeddings_health():
+    """Test the embeddings service health check."""
+    print_section("TEST: Embeddings Health Check")
+
+    try:
+        response = make_request("GET", "/api/v1/embeddings/health")
+        print_response(response)
+
+        if response.status_code == 200:
+            print("\n✅ Embeddings health check passed!")
+        else:
+            print("\n❌ Embeddings health check failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_embeddings_generate():
+    """Test the embeddings generation endpoint."""
+    print_section("TEST: Generate Embeddings")
+
+    print("Test Data:")
+    print(json.dumps(EMBEDDING_TEST_DATA, indent=2))
+    print()
+
+    try:
+        response = make_request(
+            "POST", "/api/v1/embeddings/generate", data=EMBEDDING_TEST_DATA
+        )
+        print_response(response)
+
+        if response.status_code == 200:
+            data = response.json()
+            embeddings = data.get("embeddings", [])
+            print(f"\n✅ Embeddings generation passed!")
+            print(f"   - Model: {data.get('model')}")
+            print(f"   - Dimensions: {data.get('dimensions')}")
+            print(f"   - Number of embeddings: {len(embeddings)}")
+
+            # Print shape of embeddings
+            if embeddings:
+                print(f"\n   Embedding shapes:")
+                for i, emb in enumerate(embeddings):
+                    print(f"     Text {i + 1}: {len(emb)} dimensions")
+                    print(f"       First 5 values: {emb[:5]}")
+        else:
+            print("\n❌ Embeddings generation failed!")
+    except Exception as e:
+        print(f"\n❌ Test failed with error: {str(e)}")
+
+
+def test_error_handling():
+    """Test error handling with invalid data."""
+    print_section("TEST: Error Handling")
+
+    print("Testing with invalid subtitle URL...")
+    invalid_subtitle_data = {"url": "https://invalid-url.com/video", "lang": "en"}
+
+    try:
+        response = make_request(
+            "POST", "/api/v1/subtitles/extract", data=invalid_subtitle_data
+        )
+        print_response(response)
+
+        if response.status_code >= 400:
+            print("\n✅ Error handling works correctly!")
+        else:
+            print("\n⚠️  Expected error response but got success!")
+    except Exception as e:
+        print(f"\n✅ Error handling works: {str(e)}")
+
+    print("\n" + "-" * 80 + "\n")
+    print("Testing with empty embeddings text list...")
+    invalid_embedding_data = {"texts": [], "normalize": True}
+
+    try:
+        response = make_request(
+            "POST", "/api/v1/embeddings/generate", data=invalid_embedding_data
+        )
+        print_response(response)
+
+        if response.status_code >= 400:
+            print("\n✅ Error handling works correctly!")
+        else:
+            print("\n⚠️  Expected error response but got success!")
+    except Exception as e:
+        print(f"\n✅ Error handling works: {str(e)}")
+
+
+# ============================================================================
+# MAIN TEST RUNNER
+# ============================================================================
+
+
+def run_all_tests():
+    """Run all test functions."""
+    print("\n")
+    print("+" + "=" * 78 + "+")
+    print("|" + " " * 20 + "MULTI-UTILITY SERVER API TESTS" + " " * 28 + "|")
+    print("+" + "=" * 78 + "+")
+    print(f"\nBase URL: {BASE_URL}")
+    print(
+        f"API Key: {'*' * len(API_KEY) if API_KEY != 'your-api-key-here' else 'NOT SET'}"
+    )
+
+    if API_KEY == "your-api-key-here":
+        print("\n⚠️  WARNING: Please set your API key in the API_KEY variable!")
+        print("   Some tests may fail without a valid API key.\n")
+
+    # Run all tests
+    test_health_check()
+    test_root_endpoint()
+    test_subtitles_health()
+    test_subtitles_extract()
+    test_audio_transcription()
+    test_embeddings_health()
+    test_embeddings_generate()
+    test_error_handling()
+
+    # Summary
+    print_section("TEST SUMMARY")
+    print("All tests completed!")
+    print(
+        "\nTo modify test inputs, edit the TEST_DATA section at the top of this file."
+    )
+    print("\nAvailable endpoints:")
+    print(f"  - GET  {BASE_URL}/health")
+    print(f"  - GET  {BASE_URL}/")
+    print(f"  - GET  {BASE_URL}/api/v1/subtitles/health")
+    print(f"  - POST {BASE_URL}/api/v1/subtitles/extract (requires network access)")
+    print(f"  - POST {BASE_URL}/api/v1/subtitles/transcribe (upload audio file)")
+    print(f"  - GET  {BASE_URL}/api/v1/embeddings/health")
+    print(f"  - POST {BASE_URL}/api/v1/embeddings/generate")
+    print()
+
+
+if __name__ == "__main__":
+    run_all_tests()