content-core 1.4.2__tar.gz → 1.5.0__tar.gz

{content_core-1.4.2 → content_core-1.5.0}/.gitignore

@@ -27,4 +27,6 @@ CLAUDE.md
 node_modules/
 **/notebooks/private
 
-claude-logs
+claude-logs
+specs/
+.claude/sessions

{content_core-1.4.2 → content_core-1.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.4.2
+Version: 1.5.0
 Summary: Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
@@ -548,6 +548,9 @@ GOOGLE_API_KEY=your-key-here
 # Engine Selection (optional)
 CCORE_DOCUMENT_ENGINE=auto  # auto, simple, docling
 CCORE_URL_ENGINE=auto       # auto, simple, firecrawl, jina
+
+# Audio Processing (optional)
+CCORE_AUDIO_CONCURRENCY=3   # Number of concurrent audio transcriptions (1-10, default: 3)
 ```
 
 ### Engine Selection via Environment Variables
@@ -556,9 +559,20 @@ For deployment scenarios like MCP servers or Raycast extensions, you can overrid
 
 - **`CCORE_DOCUMENT_ENGINE`**: Force document engine (`auto`, `simple`, `docling`)
 - **`CCORE_URL_ENGINE`**: Force URL engine (`auto`, `simple`, `firecrawl`, `jina`)
+- **`CCORE_AUDIO_CONCURRENCY`**: Number of concurrent audio transcriptions (1-10, default: 3)
 
 These variables take precedence over config file settings and provide explicit control for different deployment scenarios.
 
+### Audio Processing Configuration
+
+Content Core processes long audio files by splitting them into segments and transcribing them in parallel for improved performance. You can control the concurrency level to balance speed with API rate limits:
+
+- **Default**: 3 concurrent transcriptions
+- **Range**: 1-10 concurrent transcriptions
+- **Configuration**: Set via `CCORE_AUDIO_CONCURRENCY` environment variable or `extraction.audio.concurrency` in `cc_config.yaml`
+
+Higher concurrency values can speed up processing of long audio/video files but may hit API rate limits. Lower values are more conservative and suitable for accounts with lower API quotas.
+
 ### Custom Prompt Templates
 
 Content Core allows you to define custom prompt templates for content processing. By default, the library uses built-in prompts located in the `prompts` directory. However, you can create your own prompt templates and store them in a dedicated directory. To specify the location of your custom prompts, set the `PROMPT_PATH` environment variable in your `.env` file or system environment.

{content_core-1.4.2 → content_core-1.5.0}/README.md

@@ -513,6 +513,9 @@ GOOGLE_API_KEY=your-key-here
 # Engine Selection (optional)
 CCORE_DOCUMENT_ENGINE=auto  # auto, simple, docling
 CCORE_URL_ENGINE=auto       # auto, simple, firecrawl, jina
+
+# Audio Processing (optional)
+CCORE_AUDIO_CONCURRENCY=3   # Number of concurrent audio transcriptions (1-10, default: 3)
 ```
 
 ### Engine Selection via Environment Variables
@@ -521,9 +524,20 @@ For deployment scenarios like MCP servers or Raycast extensions, you can overrid
 
 - **`CCORE_DOCUMENT_ENGINE`**: Force document engine (`auto`, `simple`, `docling`)
 - **`CCORE_URL_ENGINE`**: Force URL engine (`auto`, `simple`, `firecrawl`, `jina`)
+- **`CCORE_AUDIO_CONCURRENCY`**: Number of concurrent audio transcriptions (1-10, default: 3)
 
 These variables take precedence over config file settings and provide explicit control for different deployment scenarios.
 
+### Audio Processing Configuration
+
+Content Core processes long audio files by splitting them into segments and transcribing them in parallel for improved performance. You can control the concurrency level to balance speed with API rate limits:
+
+- **Default**: 3 concurrent transcriptions
+- **Range**: 1-10 concurrent transcriptions
+- **Configuration**: Set via `CCORE_AUDIO_CONCURRENCY` environment variable or `extraction.audio.concurrency` in `cc_config.yaml`
+
+Higher concurrency values can speed up processing of long audio/video files but may hit API rate limits. Lower values are more conservative and suitable for accounts with lower API quotas.
+
 ### Custom Prompt Templates
 
 Content Core allows you to define custom prompt templates for content processing. By default, the library uses built-in prompts located in the `prompts` directory. However, you can create your own prompt templates and store them in a dedicated directory. To specify the location of your custom prompts, set the `PROMPT_PATH` environment variable in your `.env` file or system environment.

{content_core-1.4.2 → content_core-1.5.0}/docs/processors.md

@@ -36,11 +36,27 @@ Content Core uses a modular approach to process content from different sources.
 - **Returned Data**: Extracted text content or transcriptions (for media files), structured according to Content Core's schema.
 - **Location**: `src/content_core/processors/file.py`
 
-### 4. **Media Transcription Processor**
-- **Purpose**: Specifically handles transcription of audio and video files using external services or libraries.
-- **Supported Input**: Audio and video files (e.g., `.mp3`, `.mp4`).
-- **Returned Data**: Transcribed text from the media content.
-- **Location**: `src/content_core/processors/transcription.py`
+### 4. **Media Transcription Processor (Audio/Video)**
+- **Purpose**: Handles transcription of audio and video files using OpenAI Whisper API with parallel processing for improved performance
+- **Supported Input**: Audio files (`.mp3`, `.wav`, `.m4a`, `.flac`, `.ogg`) and video files (`.mp4`, `.avi`, `.mov`, `.mkv`)
+- **Returned Data**: Transcribed text from the media content, with metadata about processed segments
+- **Location**: `src/content_core/processors/audio.py`
+- **Key Features**:
+  - **Automatic Segmentation**: Files longer than 10 minutes are automatically split into segments
+  - **Parallel Processing**: Multiple segments are transcribed concurrently using `asyncio.gather()` with semaphore-based concurrency control
+  - **Configurable Concurrency**: Control the number of simultaneous transcriptions (1-10, default: 3) via `CCORE_AUDIO_CONCURRENCY` environment variable or `extraction.audio.concurrency` in YAML config
+  - **Order Preservation**: Results are assembled in correct order regardless of completion time
+  - **Efficient Resource Usage**: Semaphore prevents API rate limiting while maximizing throughput
+- **Configuration**:
+  ```yaml
+  extraction:
+    audio:
+      concurrency: 3  # Number of concurrent transcriptions (1-10)
+  ```
+- **Performance**:
+  - Short files (<10 min): Processed as single segment, no splitting overhead
+  - Long files (>10 min): Processing time scales sub-linearly with concurrency
+  - Example: 60-minute file with concurrency=3 takes ~5-7 minutes vs ~15-20 minutes with concurrency=1
 
 ### 5. **Enhanced PyMuPDF Processor (Simple Engine)**
 - **Purpose**: Optimized PDF extraction using PyMuPDF with enhanced quality flags, table detection, and optional OCR

{content_core-1.4.2 → content_core-1.5.0}/docs/usage.md

@@ -247,6 +247,121 @@ Enable OCR enhancement for:
 
 **Note**: The quality improvements (better character rendering, table detection) work automatically without requiring OCR or additional setup.
 
+## Audio Processing Configuration
+
+Content Core optimizes audio and video file processing by using parallel transcription of audio segments. This feature is particularly beneficial for long-form content like podcasts, lectures, or long videos.
+
+### How It Works
+
+1. **Automatic Segmentation**: Audio files longer than 10 minutes are automatically split into segments
+2. **Parallel Transcription**: Multiple segments are transcribed concurrently using OpenAI Whisper
+3. **Concurrency Control**: A semaphore limits the number of simultaneous API calls to prevent rate limiting
+4. **Result Assembly**: Transcriptions are joined in the correct order to produce the complete transcript
+
+### Configuration
+
+#### Via YAML Configuration
+
+Add to your `cc_config.yaml` or custom configuration file:
+
+```yaml
+extraction:
+  audio:
+    concurrency: 3  # Number of concurrent transcriptions (1-10, default: 3)
+```
+
+#### Via Environment Variable
+
+Set in your `.env` file or system environment:
+
+```plaintext
+CCORE_AUDIO_CONCURRENCY=5  # Process 5 segments simultaneously
+```
+
+The environment variable takes precedence over the YAML configuration.
+
+#### Programmatically in Python
+
+```python
+from content_core.config import set_audio_concurrency
+
+# Override audio concurrency for the current session
+set_audio_concurrency(5)
+
+# Now process audio with the new setting
+result = await cc.extract({"file_path": "long_podcast.mp3"})
+```
+
+### Performance Considerations
+
+**Choosing the Right Concurrency Level:**
+
+- **1-2 concurrent**: Conservative approach
+  - Best for: API rate limits, cost management, batch processing
+  - Processing time: Slower, but more reliable
+
+- **3-5 concurrent** (recommended): Balanced approach
+  - Best for: Most use cases, moderate file lengths
+  - Processing time: Good balance between speed and stability
+
+- **6-10 concurrent**: Aggressive approach
+  - Best for: Very long files (>1 hour), premium API tiers
+  - Processing time: Fastest, but higher risk of rate limits
+  - Note: May result in higher API costs
+
+**Example Processing Times** (approximate, for a 60-minute audio file):
+- Concurrency 1: ~15-20 minutes
+- Concurrency 3: ~5-7 minutes
+- Concurrency 10: ~2-3 minutes
+
+### Validation and Error Handling
+
+Content Core validates the concurrency setting and provides safe defaults:
+
+- **Valid range**: 1-10 concurrent transcriptions
+- **Invalid values**: Automatically fall back to default (3) with a warning logged
+- **Invalid types**: Non-integer values are rejected with a warning
+
+Example warning when using invalid value:
+```
+WARNING: Invalid CCORE_AUDIO_CONCURRENCY: '15'. Must be between 1 and 10. Using default from config.
+```
+
+### Use Cases
+
+**Podcasts and Long Interviews:**
+```python
+from content_core.config import set_audio_concurrency
+import content_core as cc
+
+# For a 2-hour podcast, use higher concurrency
+set_audio_concurrency(7)
+result = await cc.extract({"file_path": "podcast_episode_120min.mp3"})
+```
+
+**Batch Processing:**
+```python
+from content_core.config import set_audio_concurrency
+import content_core as cc
+
+# For processing multiple files sequentially, use lower concurrency
+# to avoid rate limits across all files
+set_audio_concurrency(2)
+
+for audio_file in audio_files:
+    result = await cc.extract({"file_path": audio_file})
+    # Process result...
+```
+
+**Video Transcription:**
+```python
+import content_core as cc
+
+# Videos are processed the same way - audio is extracted first, then transcribed
+result = await cc.extract({"file_path": "conference_talk.mp4"})
+print(result.content)  # Full transcript
+```
+
 ## File Type Detection
 
 Content Core uses a pure Python implementation for file type detection, eliminating the need for system dependencies like libmagic. This ensures consistent behavior across all platforms (Windows, macOS, Linux).

{content_core-1.4.2 → content_core-1.5.0}/examples/main.py

@@ -6,10 +6,9 @@ This script processes all files in the input_content/ directory and URLs from ur
 converting them to Markdown format and saving the results to separate files.
 """
 
-import os
 import sys
 from pathlib import Path
-from typing import List, Tuple
+from typing import List
 from urllib.parse import urlparse
 
 from loguru import logger

content_core-1.5.0/notebooks/extraction.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "444fcc1f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2025-09-26 16:49:15.616\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcontent_core.processors.audio\u001b[0m:\u001b[36mextract_audio_data\u001b[0m:\u001b[36m123\u001b[0m - \u001b[1mAudio is longer than 10 minutes (675.31s), splitting into 2 segments\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MoviePy - Writing audio in /var/folders/cl/346yd2sd3vz399s0m2c_ynvr0000gn/T/tmp6zx9axd4/OAT - Aula 2 v2 - Levi Rezende_audio_001.mp3\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                        \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MoviePy - Done.\n",
+      "MoviePy - Writing audio in /var/folders/cl/346yd2sd3vz399s0m2c_ynvr0000gn/T/tmp6zx9axd4/OAT - Aula 2 v2 - Levi Rezende_audio_002.mp3\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                      \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MoviePy - Done.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2025-09-26 16:49:54.566\u001b[0m | \u001b[31m\u001b[1mERROR   \u001b[0m | \u001b[36mcontent_core.processors.audio\u001b[0m:\u001b[36mextract_audio_data\u001b[0m:\u001b[36m156\u001b[0m - \u001b[31m\u001b[1mError processing audio: \u001b[0m\n",
+      "\u001b[32m2025-09-26 16:49:54.587\u001b[0m | \u001b[31m\u001b[1mERROR   \u001b[0m | \u001b[36mcontent_core.processors.audio\u001b[0m:\u001b[36mextract_audio_data\u001b[0m:\u001b[36m157\u001b[0m - \u001b[31m\u001b[1mTraceback (most recent call last):\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py\", line 101, in map_httpcore_exceptions\n",
+      "    yield\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py\", line 394, in handle_async_request\n",
+      "    resp = await self._pool.handle_async_request(req)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection_pool.py\", line 256, in handle_async_request\n",
+      "    raise exc from None\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection_pool.py\", line 236, in handle_async_request\n",
+      "    response = await connection.handle_async_request(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection.py\", line 103, in handle_async_request\n",
+      "    return await self._connection.handle_async_request(request)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py\", line 136, in handle_async_request\n",
+      "    raise exc\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py\", line 106, in handle_async_request\n",
+      "    ) = await self._receive_response_headers(**kwargs)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py\", line 177, in _receive_response_headers\n",
+      "    event = await self._receive_event(timeout=timeout)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py\", line 217, in _receive_event\n",
+      "    data = await self._network_stream.read(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_backends/anyio.py\", line 32, in read\n",
+      "    with map_exceptions(exc_map):\n",
+      "  File \"/Users/luisnovo/.local/share/uv/python/cpython-3.10.6-macos-aarch64-none/lib/python3.10/contextlib.py\", line 153, in __exit__\n",
+      "    self.gen.throw(typ, value, traceback)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_exceptions.py\", line 14, in map_exceptions\n",
+      "    raise to_exc(exc) from exc\n",
+      "httpcore.ReadTimeout\n",
+      "\n",
+      "The above exception was the direct cause of the following exception:\n",
+      "\n",
+      "Traceback (most recent call last):\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/src/content_core/processors/audio.py\", line 146, in extract_audio_data\n",
+      "    transcription = await transcribe_audio_segment(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/src/content_core/processors/audio.py\", line 103, in transcribe_audio_segment\n",
+      "    return (await model.atranscribe(audio_file)).text\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/esperanto/providers/stt/openai.py\", line 158, in atranscribe\n",
+      "    response = await self.async_client.post(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1859, in post\n",
+      "    return await self.request(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1540, in request\n",
+      "    return await self.send(request, auth=auth, follow_redirects=follow_redirects)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1629, in send\n",
+      "    response = await self._send_handling_auth(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1657, in _send_handling_auth\n",
+      "    response = await self._send_handling_redirects(\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1694, in _send_handling_redirects\n",
+      "    response = await self._send_single_request(request)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py\", line 1730, in _send_single_request\n",
+      "    response = await transport.handle_async_request(request)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py\", line 393, in handle_async_request\n",
+      "    with map_httpcore_exceptions():\n",
+      "  File \"/Users/luisnovo/.local/share/uv/python/cpython-3.10.6-macos-aarch64-none/lib/python3.10/contextlib.py\", line 153, in __exit__\n",
+      "    self.gen.throw(typ, value, traceback)\n",
+      "  File \"/Users/luisnovo/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py\", line 118, in map_httpcore_exceptions\n",
+      "    raise mapped_exc(message) from exc\n",
+      "httpx.ReadTimeout\n",
+      "\u001b[0m\n"
+     ]
+    },
+    {
+     "ename": "ReadTimeout",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mReadTimeout\u001b[0m                               Traceback (most recent call last)",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py:101\u001b[0m, in \u001b[0;36mmap_httpcore_exceptions\u001b[0;34m()\u001b[0m\n\u001b[1;32m    100\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 101\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m\n\u001b[1;32m    102\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py:394\u001b[0m, in \u001b[0;36mAsyncHTTPTransport.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    393\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_httpcore_exceptions():\n\u001b[0;32m--> 394\u001b[0m     resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pool\u001b[38;5;241m.\u001b[39mhandle_async_request(req)\n\u001b[1;32m    396\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resp\u001b[38;5;241m.\u001b[39mstream, typing\u001b[38;5;241m.\u001b[39mAsyncIterable)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection_pool.py:256\u001b[0m, in \u001b[0;36mAsyncConnectionPool.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    255\u001b[0m     \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_connections(closing)\n\u001b[0;32m--> 256\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m exc \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    258\u001b[0m \u001b[38;5;66;03m# Return the response. Note that in this case we still have to manage\u001b[39;00m\n\u001b[1;32m    259\u001b[0m \u001b[38;5;66;03m# the point at which the response is closed.\u001b[39;00m\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection_pool.py:236\u001b[0m, in \u001b[0;36mAsyncConnectionPool.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    234\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    235\u001b[0m     \u001b[38;5;66;03m# Send the request on the assigned connection.\u001b[39;00m\n\u001b[0;32m--> 236\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m connection\u001b[38;5;241m.\u001b[39mhandle_async_request(\n\u001b[1;32m    237\u001b[0m         pool_request\u001b[38;5;241m.\u001b[39mrequest\n\u001b[1;32m    238\u001b[0m     )\n\u001b[1;32m    239\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ConnectionNotAvailable:\n\u001b[1;32m    240\u001b[0m     \u001b[38;5;66;03m# In some cases a connection may initially be available to\u001b[39;00m\n\u001b[1;32m    241\u001b[0m     \u001b[38;5;66;03m# handle a request, but then become unavailable.\u001b[39;00m\n\u001b[1;32m    242\u001b[0m     \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[1;32m    243\u001b[0m     \u001b[38;5;66;03m# In this case we clear the connection and try again.\u001b[39;00m\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/connection.py:103\u001b[0m, in \u001b[0;36mAsyncHTTPConnection.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    101\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m exc\n\u001b[0;32m--> 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_connection\u001b[38;5;241m.\u001b[39mhandle_async_request(request)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py:136\u001b[0m, in \u001b[0;36mAsyncHTTP11Connection.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    135\u001b[0m         \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_response_closed()\n\u001b[0;32m--> 136\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py:106\u001b[0m, in \u001b[0;36mAsyncHTTP11Connection.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m     97\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mwith\u001b[39;00m Trace(\n\u001b[1;32m     98\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mreceive_response_headers\u001b[39m\u001b[38;5;124m\"\u001b[39m, logger, request, kwargs\n\u001b[1;32m     99\u001b[0m ) \u001b[38;5;28;01mas\u001b[39;00m trace:\n\u001b[1;32m    100\u001b[0m     (\n\u001b[1;32m    101\u001b[0m         http_version,\n\u001b[1;32m    102\u001b[0m         status,\n\u001b[1;32m    103\u001b[0m         reason_phrase,\n\u001b[1;32m    104\u001b[0m         headers,\n\u001b[1;32m    105\u001b[0m         trailing_data,\n\u001b[0;32m--> 106\u001b[0m     ) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_receive_response_headers(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    107\u001b[0m     trace\u001b[38;5;241m.\u001b[39mreturn_value \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    108\u001b[0m         http_version,\n\u001b[1;32m    109\u001b[0m         status,\n\u001b[1;32m    110\u001b[0m         reason_phrase,\n\u001b[1;32m    111\u001b[0m         headers,\n\u001b[1;32m    112\u001b[0m     )\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py:177\u001b[0m, in \u001b[0;36mAsyncHTTP11Connection._receive_response_headers\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    176\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 177\u001b[0m     event \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_receive_event(timeout\u001b[38;5;241m=\u001b[39mtimeout)\n\u001b[1;32m    178\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(event, h11\u001b[38;5;241m.\u001b[39mResponse):\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_async/http11.py:217\u001b[0m, in \u001b[0;36mAsyncHTTP11Connection._receive_event\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    216\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m event \u001b[38;5;129;01mis\u001b[39;00m h11\u001b[38;5;241m.\u001b[39mNEED_DATA:\n\u001b[0;32m--> 217\u001b[0m     data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_network_stream\u001b[38;5;241m.\u001b[39mread(\n\u001b[1;32m    218\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mREAD_NUM_BYTES, timeout\u001b[38;5;241m=\u001b[39mtimeout\n\u001b[1;32m    219\u001b[0m     )\n\u001b[1;32m    221\u001b[0m     \u001b[38;5;66;03m# If we feed this case through h11 we'll raise an exception like:\u001b[39;00m\n\u001b[1;32m    222\u001b[0m     \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[1;32m    223\u001b[0m     \u001b[38;5;66;03m#     httpcore.RemoteProtocolError: can't handle event type\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    227\u001b[0m     \u001b[38;5;66;03m# perspective. Instead we handle this case distinctly and treat\u001b[39;00m\n\u001b[1;32m    228\u001b[0m     \u001b[38;5;66;03m# it as a ConnectError.\u001b[39;00m\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_backends/anyio.py:32\u001b[0m, in \u001b[0;36mAnyIOStream.read\u001b[0;34m(self, max_bytes, timeout)\u001b[0m\n\u001b[1;32m     26\u001b[0m exc_map \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m     27\u001b[0m     \u001b[38;5;167;01mTimeoutError\u001b[39;00m: ReadTimeout,\n\u001b[1;32m     28\u001b[0m     anyio\u001b[38;5;241m.\u001b[39mBrokenResourceError: ReadError,\n\u001b[1;32m     29\u001b[0m     anyio\u001b[38;5;241m.\u001b[39mClosedResourceError: ReadError,\n\u001b[1;32m     30\u001b[0m     anyio\u001b[38;5;241m.\u001b[39mEndOfStream: ReadError,\n\u001b[1;32m     31\u001b[0m }\n\u001b[0;32m---> 32\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_exceptions(exc_map):\n\u001b[1;32m     33\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m anyio\u001b[38;5;241m.\u001b[39mfail_after(timeout):\n",
+      "File \u001b[0;32m~/.local/share/uv/python/cpython-3.10.6-macos-aarch64-none/lib/python3.10/contextlib.py:153\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__exit__\u001b[0;34m(self, typ, value, traceback)\u001b[0m\n\u001b[1;32m    152\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 153\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgen\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mthrow\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtyp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtraceback\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    154\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    155\u001b[0m     \u001b[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001b[39;00m\n\u001b[1;32m    156\u001b[0m     \u001b[38;5;66;03m# was passed to throw().  This prevents a StopIteration\u001b[39;00m\n\u001b[1;32m    157\u001b[0m     \u001b[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001b[39;00m\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpcore/_exceptions.py:14\u001b[0m, in \u001b[0;36mmap_exceptions\u001b[0;34m(map)\u001b[0m\n\u001b[1;32m     13\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(exc, from_exc):\n\u001b[0;32m---> 14\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m to_exc(exc) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mexc\u001b[39;00m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m\n",
+      "\u001b[0;31mReadTimeout\u001b[0m: ",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[0;31mReadTimeout\u001b[0m                               Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 8\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mcontent_core\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m extract_content\n\u001b[1;32m      4\u001b[0m lesson_source \u001b[38;5;241m=\u001b[39m ProcessSourceInput(\n\u001b[1;32m      5\u001b[0m     file_path\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m/Users/luisnovo/dev/projetos/snl/adaptive-learning-novo/data/input/Oportunidade ao Alcance de Todos/OAT - Aula 2 v2 - Levi Rezende.mp4\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m      6\u001b[0m )\n\u001b[0;32m----> 8\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m extract_content(lesson_source)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/src/content_core/content/extraction/__init__.py:12\u001b[0m, in \u001b[0;36mextract_content\u001b[0;34m(data)\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(data, \u001b[38;5;28mdict\u001b[39m):\n\u001b[1;32m     11\u001b[0m     data \u001b[38;5;241m=\u001b[39m ProcessSourceInput(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mdata)\n\u001b[0;32m---> 12\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m graph\u001b[38;5;241m.\u001b[39mainvoke(data)\n\u001b[1;32m     13\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ProcessSourceOutput(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mresult)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/pregel/__init__.py:2920\u001b[0m, in \u001b[0;36mPregel.ainvoke\u001b[0;34m(self, input, config, stream_mode, print_mode, output_keys, interrupt_before, interrupt_after, **kwargs)\u001b[0m\n\u001b[1;32m   2917\u001b[0m chunks: \u001b[38;5;28mlist\u001b[39m[\u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m|\u001b[39m Any] \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m   2918\u001b[0m interrupts: \u001b[38;5;28mlist\u001b[39m[Interrupt] \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m-> 2920\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mastream(\n\u001b[1;32m   2921\u001b[0m     \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m   2922\u001b[0m     config,\n\u001b[1;32m   2923\u001b[0m     stream_mode\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mupdates\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvalues\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m   2924\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m stream_mode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvalues\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   2925\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m stream_mode,\n\u001b[1;32m   2926\u001b[0m     print_mode\u001b[38;5;241m=\u001b[39mprint_mode,\n\u001b[1;32m   2927\u001b[0m     output_keys\u001b[38;5;241m=\u001b[39moutput_keys,\n\u001b[1;32m   2928\u001b[0m     interrupt_before\u001b[38;5;241m=\u001b[39minterrupt_before,\n\u001b[1;32m   2929\u001b[0m     interrupt_after\u001b[38;5;241m=\u001b[39minterrupt_after,\n\u001b[1;32m   2930\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m   2931\u001b[0m ):\n\u001b[1;32m   2932\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m stream_mode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvalues\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   2933\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(chunk) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/pregel/__init__.py:2768\u001b[0m, in \u001b[0;36mPregel.astream\u001b[0;34m(self, input, config, stream_mode, print_mode, output_keys, interrupt_before, interrupt_after, checkpoint_during, debug, subgraphs)\u001b[0m\n\u001b[1;32m   2766\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m task \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m loop\u001b[38;5;241m.\u001b[39mamatch_cached_writes():\n\u001b[1;32m   2767\u001b[0m     loop\u001b[38;5;241m.\u001b[39moutput_writes(task\u001b[38;5;241m.\u001b[39mid, task\u001b[38;5;241m.\u001b[39mwrites, cached\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m-> 2768\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m _ \u001b[38;5;129;01min\u001b[39;00m runner\u001b[38;5;241m.\u001b[39matick(\n\u001b[1;32m   2769\u001b[0m     [t \u001b[38;5;28;01mfor\u001b[39;00m t \u001b[38;5;129;01min\u001b[39;00m loop\u001b[38;5;241m.\u001b[39mtasks\u001b[38;5;241m.\u001b[39mvalues() \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m t\u001b[38;5;241m.\u001b[39mwrites],\n\u001b[1;32m   2770\u001b[0m     timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstep_timeout,\n\u001b[1;32m   2771\u001b[0m     get_waiter\u001b[38;5;241m=\u001b[39mget_waiter,\n\u001b[1;32m   2772\u001b[0m     schedule_task\u001b[38;5;241m=\u001b[39mloop\u001b[38;5;241m.\u001b[39maaccept_push,\n\u001b[1;32m   2773\u001b[0m ):\n\u001b[1;32m   2774\u001b[0m     \u001b[38;5;66;03m# emit output\u001b[39;00m\n\u001b[1;32m   2775\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m o \u001b[38;5;129;01min\u001b[39;00m _output(\n\u001b[1;32m   2776\u001b[0m         stream_mode,\n\u001b[1;32m   2777\u001b[0m         print_mode,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   2780\u001b[0m         asyncio\u001b[38;5;241m.\u001b[39mQueueEmpty,\n\u001b[1;32m   2781\u001b[0m     ):\n\u001b[1;32m   2782\u001b[0m         \u001b[38;5;28;01myield\u001b[39;00m o\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/pregel/runner.py:295\u001b[0m, in \u001b[0;36mPregelRunner.atick\u001b[0;34m(self, tasks, reraise, timeout, retry_policy, get_waiter, schedule_task)\u001b[0m\n\u001b[1;32m    293\u001b[0m t \u001b[38;5;241m=\u001b[39m tasks[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    294\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 295\u001b[0m     \u001b[38;5;28;01mawait\u001b[39;00m arun_with_retry(\n\u001b[1;32m    296\u001b[0m         t,\n\u001b[1;32m    297\u001b[0m         retry_policy,\n\u001b[1;32m    298\u001b[0m         stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muse_astream,\n\u001b[1;32m    299\u001b[0m         configurable\u001b[38;5;241m=\u001b[39m{\n\u001b[1;32m    300\u001b[0m             CONFIG_KEY_CALL: partial(\n\u001b[1;32m    301\u001b[0m                 _acall,\n\u001b[1;32m    302\u001b[0m                 weakref\u001b[38;5;241m.\u001b[39mref(t),\n\u001b[1;32m    303\u001b[0m                 stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muse_astream,\n\u001b[1;32m    304\u001b[0m                 retry_policy\u001b[38;5;241m=\u001b[39mretry_policy,\n\u001b[1;32m    305\u001b[0m                 futures\u001b[38;5;241m=\u001b[39mweakref\u001b[38;5;241m.\u001b[39mref(futures),\n\u001b[1;32m    306\u001b[0m                 schedule_task\u001b[38;5;241m=\u001b[39mschedule_task,\n\u001b[1;32m    307\u001b[0m                 submit\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubmit,\n\u001b[1;32m    308\u001b[0m                 loop\u001b[38;5;241m=\u001b[39mloop,\n\u001b[1;32m    309\u001b[0m             ),\n\u001b[1;32m    310\u001b[0m         },\n\u001b[1;32m    311\u001b[0m     )\n\u001b[1;32m    312\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcommit(t, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m    313\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/pregel/retry.py:137\u001b[0m, in \u001b[0;36marun_with_retry\u001b[0;34m(task, retry_policy, stream, match_cached_writes, configurable)\u001b[0m\n\u001b[1;32m    135\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m    136\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 137\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m task\u001b[38;5;241m.\u001b[39mproc\u001b[38;5;241m.\u001b[39mainvoke(task\u001b[38;5;241m.\u001b[39minput, config)\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ParentCommand \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    139\u001b[0m     ns: \u001b[38;5;28mstr\u001b[39m \u001b[38;5;241m=\u001b[39m config[CONF][CONFIG_KEY_CHECKPOINT_NS]\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/utils/runnable.py:676\u001b[0m, in \u001b[0;36mRunnableSeq.ainvoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    672\u001b[0m             \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m asyncio\u001b[38;5;241m.\u001b[39mcreate_task(\n\u001b[1;32m    673\u001b[0m                 step\u001b[38;5;241m.\u001b[39mainvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs), context\u001b[38;5;241m=\u001b[39mcontext\n\u001b[1;32m    674\u001b[0m             )\n\u001b[1;32m    675\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 676\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m step\u001b[38;5;241m.\u001b[39mainvoke(\u001b[38;5;28minput\u001b[39m, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    677\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    678\u001b[0m     \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m step\u001b[38;5;241m.\u001b[39mainvoke(\u001b[38;5;28minput\u001b[39m, config)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/langgraph/utils/runnable.py:440\u001b[0m, in \u001b[0;36mRunnableCallable.ainvoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    438\u001b[0m         \u001b[38;5;28;01mawait\u001b[39;00m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(ret)\n\u001b[1;32m    439\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 440\u001b[0m     ret \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mafunc(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    441\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrecurse \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(ret, Runnable):\n\u001b[1;32m    442\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m ret\u001b[38;5;241m.\u001b[39mainvoke(\u001b[38;5;28minput\u001b[39m, config)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/src/content_core/processors/audio.py:146\u001b[0m, in \u001b[0;36mextract_audio_data\u001b[0;34m(data)\u001b[0m\n\u001b[1;32m    144\u001b[0m transcriptions \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m    145\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m audio_file \u001b[38;5;129;01min\u001b[39;00m output_files:\n\u001b[0;32m--> 146\u001b[0m     transcription \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m transcribe_audio_segment(\n\u001b[1;32m    147\u001b[0m         audio_file, speech_to_text_model\n\u001b[1;32m    148\u001b[0m     )\n\u001b[1;32m    149\u001b[0m     transcriptions\u001b[38;5;241m.\u001b[39mappend(transcription)\n\u001b[1;32m    151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m    152\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maudio_files\u001b[39m\u001b[38;5;124m\"\u001b[39m: output_files},\n\u001b[1;32m    153\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(transcriptions),\n\u001b[1;32m    154\u001b[0m }\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/src/content_core/processors/audio.py:103\u001b[0m, in \u001b[0;36mtranscribe_audio_segment\u001b[0;34m(audio_file, model)\u001b[0m\n\u001b[1;32m    101\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mtranscribe_audio_segment\u001b[39m(audio_file, model):\n\u001b[1;32m    102\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Transcribe a single audio segment asynchronously\"\"\"\u001b[39;00m\n\u001b[0;32m--> 103\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m (\u001b[38;5;28;01mawait\u001b[39;00m model\u001b[38;5;241m.\u001b[39matranscribe(audio_file))\u001b[38;5;241m.\u001b[39mtext\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/esperanto/providers/stt/openai.py:158\u001b[0m, in \u001b[0;36mOpenAISpeechToTextModel.atranscribe\u001b[0;34m(self, audio_file, language, prompt)\u001b[0m\n\u001b[1;32m    156\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(audio_file, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m    157\u001b[0m         files \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfile\u001b[39m\u001b[38;5;124m\"\u001b[39m: (audio_file, f, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maudio/mpeg\u001b[39m\u001b[38;5;124m\"\u001b[39m)}\n\u001b[0;32m--> 158\u001b[0m         response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39masync_client\u001b[38;5;241m.\u001b[39mpost(\n\u001b[1;32m    159\u001b[0m             \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_url\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/audio/transcriptions\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    160\u001b[0m             headers\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_headers(),\n\u001b[1;32m    161\u001b[0m             files\u001b[38;5;241m=\u001b[39mfiles,\n\u001b[1;32m    162\u001b[0m             data\u001b[38;5;241m=\u001b[39mkwargs\n\u001b[1;32m    163\u001b[0m         )\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    165\u001b[0m     \u001b[38;5;66;03m# For BinaryIO, send the file object directly\u001b[39;00m\n\u001b[1;32m    166\u001b[0m     filename \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(audio_file, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124maudio.mp3\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1859\u001b[0m, in \u001b[0;36mAsyncClient.post\u001b[0;34m(self, url, content, data, files, json, params, headers, cookies, auth, follow_redirects, timeout, extensions)\u001b[0m\n\u001b[1;32m   1838\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1839\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1840\u001b[0m     url: URL \u001b[38;5;241m|\u001b[39m \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1852\u001b[0m     extensions: RequestExtensions \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1853\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Response:\n\u001b[1;32m   1854\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1855\u001b[0m \u001b[38;5;124;03m    Send a `POST` request.\u001b[39;00m\n\u001b[1;32m   1856\u001b[0m \n\u001b[1;32m   1857\u001b[0m \u001b[38;5;124;03m    **Parameters**: See `httpx.request`.\u001b[39;00m\n\u001b[1;32m   1858\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1859\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequest(\n\u001b[1;32m   1860\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPOST\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m   1861\u001b[0m         url,\n\u001b[1;32m   1862\u001b[0m         content\u001b[38;5;241m=\u001b[39mcontent,\n\u001b[1;32m   1863\u001b[0m         data\u001b[38;5;241m=\u001b[39mdata,\n\u001b[1;32m   1864\u001b[0m         files\u001b[38;5;241m=\u001b[39mfiles,\n\u001b[1;32m   1865\u001b[0m         json\u001b[38;5;241m=\u001b[39mjson,\n\u001b[1;32m   1866\u001b[0m         params\u001b[38;5;241m=\u001b[39mparams,\n\u001b[1;32m   1867\u001b[0m         headers\u001b[38;5;241m=\u001b[39mheaders,\n\u001b[1;32m   1868\u001b[0m         cookies\u001b[38;5;241m=\u001b[39mcookies,\n\u001b[1;32m   1869\u001b[0m         auth\u001b[38;5;241m=\u001b[39mauth,\n\u001b[1;32m   1870\u001b[0m         follow_redirects\u001b[38;5;241m=\u001b[39mfollow_redirects,\n\u001b[1;32m   1871\u001b[0m         timeout\u001b[38;5;241m=\u001b[39mtimeout,\n\u001b[1;32m   1872\u001b[0m         extensions\u001b[38;5;241m=\u001b[39mextensions,\n\u001b[1;32m   1873\u001b[0m     )\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1540\u001b[0m, in \u001b[0;36mAsyncClient.request\u001b[0;34m(self, method, url, content, data, files, json, params, headers, cookies, auth, follow_redirects, timeout, extensions)\u001b[0m\n\u001b[1;32m   1525\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(message, \u001b[38;5;167;01mDeprecationWarning\u001b[39;00m, stacklevel\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m)\n\u001b[1;32m   1527\u001b[0m request \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuild_request(\n\u001b[1;32m   1528\u001b[0m     method\u001b[38;5;241m=\u001b[39mmethod,\n\u001b[1;32m   1529\u001b[0m     url\u001b[38;5;241m=\u001b[39murl,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1538\u001b[0m     extensions\u001b[38;5;241m=\u001b[39mextensions,\n\u001b[1;32m   1539\u001b[0m )\n\u001b[0;32m-> 1540\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msend(request, auth\u001b[38;5;241m=\u001b[39mauth, follow_redirects\u001b[38;5;241m=\u001b[39mfollow_redirects)\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1629\u001b[0m, in \u001b[0;36mAsyncClient.send\u001b[0;34m(self, request, stream, auth, follow_redirects)\u001b[0m\n\u001b[1;32m   1625\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_set_timeout(request)\n\u001b[1;32m   1627\u001b[0m auth \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_build_request_auth(request, auth)\n\u001b[0;32m-> 1629\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_send_handling_auth(\n\u001b[1;32m   1630\u001b[0m     request,\n\u001b[1;32m   1631\u001b[0m     auth\u001b[38;5;241m=\u001b[39mauth,\n\u001b[1;32m   1632\u001b[0m     follow_redirects\u001b[38;5;241m=\u001b[39mfollow_redirects,\n\u001b[1;32m   1633\u001b[0m     history\u001b[38;5;241m=\u001b[39m[],\n\u001b[1;32m   1634\u001b[0m )\n\u001b[1;32m   1635\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1636\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m stream:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1657\u001b[0m, in \u001b[0;36mAsyncClient._send_handling_auth\u001b[0;34m(self, request, auth, follow_redirects, history)\u001b[0m\n\u001b[1;32m   1654\u001b[0m request \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m auth_flow\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__anext__\u001b[39m()\n\u001b[1;32m   1656\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m-> 1657\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_send_handling_redirects(\n\u001b[1;32m   1658\u001b[0m         request,\n\u001b[1;32m   1659\u001b[0m         follow_redirects\u001b[38;5;241m=\u001b[39mfollow_redirects,\n\u001b[1;32m   1660\u001b[0m         history\u001b[38;5;241m=\u001b[39mhistory,\n\u001b[1;32m   1661\u001b[0m     )\n\u001b[1;32m   1662\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1663\u001b[0m         \u001b[38;5;28;01mtry\u001b[39;00m:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1694\u001b[0m, in \u001b[0;36mAsyncClient._send_handling_redirects\u001b[0;34m(self, request, follow_redirects, history)\u001b[0m\n\u001b[1;32m   1691\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m hook \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_event_hooks[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrequest\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[1;32m   1692\u001b[0m     \u001b[38;5;28;01mawait\u001b[39;00m hook(request)\n\u001b[0;32m-> 1694\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_send_single_request(request)\n\u001b[1;32m   1695\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1696\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m hook \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_event_hooks[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresponse\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_client.py:1730\u001b[0m, in \u001b[0;36mAsyncClient._send_single_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m   1725\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[1;32m   1726\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAttempted to send an sync request with an AsyncClient instance.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1727\u001b[0m     )\n\u001b[1;32m   1729\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39mrequest):\n\u001b[0;32m-> 1730\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m transport\u001b[38;5;241m.\u001b[39mhandle_async_request(request)\n\u001b[1;32m   1732\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response\u001b[38;5;241m.\u001b[39mstream, AsyncByteStream)\n\u001b[1;32m   1733\u001b[0m response\u001b[38;5;241m.\u001b[39mrequest \u001b[38;5;241m=\u001b[39m request\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py:393\u001b[0m, in \u001b[0;36mAsyncHTTPTransport.handle_async_request\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    379\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mhttpcore\u001b[39;00m\n\u001b[1;32m    381\u001b[0m req \u001b[38;5;241m=\u001b[39m httpcore\u001b[38;5;241m.\u001b[39mRequest(\n\u001b[1;32m    382\u001b[0m     method\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mmethod,\n\u001b[1;32m    383\u001b[0m     url\u001b[38;5;241m=\u001b[39mhttpcore\u001b[38;5;241m.\u001b[39mURL(\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    391\u001b[0m     extensions\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mextensions,\n\u001b[1;32m    392\u001b[0m )\n\u001b[0;32m--> 393\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_httpcore_exceptions():\n\u001b[1;32m    394\u001b[0m     resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pool\u001b[38;5;241m.\u001b[39mhandle_async_request(req)\n\u001b[1;32m    396\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resp\u001b[38;5;241m.\u001b[39mstream, typing\u001b[38;5;241m.\u001b[39mAsyncIterable)\n",
+      "File \u001b[0;32m~/.local/share/uv/python/cpython-3.10.6-macos-aarch64-none/lib/python3.10/contextlib.py:153\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__exit__\u001b[0;34m(self, typ, value, traceback)\u001b[0m\n\u001b[1;32m    151\u001b[0m     value \u001b[38;5;241m=\u001b[39m typ()\n\u001b[1;32m    152\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 153\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgen\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mthrow\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtyp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtraceback\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    154\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    155\u001b[0m     \u001b[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001b[39;00m\n\u001b[1;32m    156\u001b[0m     \u001b[38;5;66;03m# was passed to throw().  This prevents a StopIteration\u001b[39;00m\n\u001b[1;32m    157\u001b[0m     \u001b[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001b[39;00m\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m exc \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m value\n",
+      "File \u001b[0;32m~/dev/projetos/content-core/.venv/lib/python3.10/site-packages/httpx/_transports/default.py:118\u001b[0m, in \u001b[0;36mmap_httpcore_exceptions\u001b[0;34m()\u001b[0m\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m\n\u001b[1;32m    117\u001b[0m message \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(exc)\n\u001b[0;32m--> 118\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m mapped_exc(message) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mexc\u001b[39;00m\n",
+      "\u001b[0;31mReadTimeout\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "from content_core.common import ProcessSourceInput\n",
+    "from content_core import extract_content\n",
+    "\n",
+    "lesson_source = ProcessSourceInput(\n",
+    "    file_path=\"/Users/luisnovo/dev/projetos/snl/adaptive-learning-novo/data/input/Oportunidade ao Alcance de Todos/OAT - Aula 2 v2 - Levi Rezende.mp4\",\n",
+    ")\n",
+    "    \n",
+    "result = await extract_content(lesson_source)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

{content_core-1.4.2 → content_core-1.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "content-core"
-version = "1.4.2"
+version = "1.5.0"
 description = "Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server"
 readme = "README.md"
 homepage = "https://github.com/lfnovo/content-core"
@@ -70,3 +70,4 @@ dev = [
 pythonpath = ["src"]
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "function"
+asyncio_default_test_loop_scope = "function"

{content_core-1.4.2 → content_core-1.5.0}/src/content_core/cc_config.yaml

@@ -32,6 +32,8 @@ summary_model:
 extraction:
   document_engine: auto  # auto | simple | docling - for files/documents
   url_engine: auto  # auto | simple | firecrawl | jina | docling - for URLs
+  audio:
+    concurrency: 3              # Number of concurrent audio transcriptions (1-10)
   docling:
     output_format: markdown  # markdown | html | json
   pymupdf:

{content_core-1.4.2 → content_core-1.5.0}/src/content_core/config.py

@@ -70,6 +70,61 @@ def get_url_engine():
         return env_engine
     return CONFIG.get("extraction", {}).get("url_engine", "auto")
 
+def get_audio_concurrency():
+    """
+    Get audio concurrency with environment variable override and validation.
+
+    Returns the configured number of concurrent audio transcriptions, with automatic
+    validation and fallback to safe defaults.
+
+    Configuration priority (highest to lowest):
+    1. CCORE_AUDIO_CONCURRENCY environment variable
+    2. extraction.audio.concurrency in YAML config
+    3. Default value: 3
+
+    Returns:
+        int: Number of concurrent transcriptions (1-10)
+
+    Validation:
+        - Values must be integers between 1 and 10 (inclusive)
+        - Invalid values (out of range, non-integer, etc.) automatically fall back to default
+        - A warning is logged when invalid values are detected
+
+    Examples:
+        >>> import os
+        >>> os.environ["CCORE_AUDIO_CONCURRENCY"] = "5"
+        >>> get_audio_concurrency()
+        5
+
+        >>> os.environ["CCORE_AUDIO_CONCURRENCY"] = "20"  # Too high
+        >>> get_audio_concurrency()  # Falls back to default
+        3
+    """
+    env_concurrency = os.environ.get("CCORE_AUDIO_CONCURRENCY")
+    if env_concurrency:
+        try:
+            concurrency = int(env_concurrency)
+            if concurrency < 1 or concurrency > 10:
+                # Import logger here to avoid circular imports
+                from content_core.logging import logger
+                logger.warning(
+                    f"Invalid CCORE_AUDIO_CONCURRENCY: '{env_concurrency}'. "
+                    f"Must be between 1 and 10. "
+                    f"Using default from config."
+                )
+                return CONFIG.get("extraction", {}).get("audio", {}).get("concurrency", 3)
+            return concurrency
+        except ValueError:
+            # Import logger here to avoid circular imports
+            from content_core.logging import logger
+            logger.warning(
+                f"Invalid CCORE_AUDIO_CONCURRENCY: '{env_concurrency}'. "
+                f"Must be a valid integer. "
+                f"Using default from config."
+            )
+            return CONFIG.get("extraction", {}).get("audio", {}).get("concurrency", 3)
+    return CONFIG.get("extraction", {}).get("audio", {}).get("concurrency", 3)
+
 # Programmatic config overrides: use in notebooks or scripts
 def set_document_engine(engine: str):
     """Override the document extraction engine ('auto', 'simple', or 'docling')."""
@@ -102,3 +157,19 @@ def set_pymupdf_ocr_fallback(enabled: bool):
     extraction = CONFIG.setdefault("extraction", {})
     pymupdf_cfg = extraction.setdefault("pymupdf", {})
     pymupdf_cfg["ocr_fallback"] = enabled
+
+def set_audio_concurrency(concurrency: int):
+    """
+    Override the audio concurrency setting (1-10).
+
+    Args:
+        concurrency (int): Number of concurrent audio transcriptions (1-10)
+
+    Raises:
+        ValueError: If concurrency is not between 1 and 10
+    """
+    if not isinstance(concurrency, int) or concurrency < 1 or concurrency > 10:
+        raise ValueError(f"Audio concurrency must be an integer between 1 and 10, got: {concurrency}")
+    extraction = CONFIG.setdefault("extraction", {})
+    audio_cfg = extraction.setdefault("audio", {})
+    audio_cfg["concurrency"] = concurrency

{content_core-1.4.2 → content_core-1.5.0}/src/content_core/content/identification/file_detector.py

@@ -3,10 +3,9 @@ Pure Python file type detection using magic bytes and content analysis.
 Replaces libmagic dependency with a lightweight implementation.
 """
 
-import os
 import zipfile
 from pathlib import Path
-from typing import Dict, Optional, Tuple
+from typing import Dict, Optional
 
 from content_core.common.exceptions import UnsupportedTypeException
 from content_core.logging import logger