Updated: requirement.txt some deppendencies needed newer versions

REQUIREMENTS_FIX.md

@@ -0,0 +1,68 @@
+# Requirements.txt Fix Summary
+
+## The Bug
+**Error**: `ModuleNotFoundError: No module named 'langchain_core.messages.content'`
+
+**Root Cause**: Version incompatibility between `langchain-mcp-adapters>=0.1.0` and `langchain-core>=0.3.0`. The older versions of langchain-core don't have the `messages.content` module that the MCP adapters require.
+
+## Critical Changes Made
+
+### 1. Fixed LangChain Version Constraints (CRITICAL FIX)
+```diff
+- langchain-core>=0.3.0
++ langchain-core>=0.3.80,<0.4.0
+
+- langchain-mcp-adapters>=0.1.0
++ langchain-mcp-adapters>=0.1.14,<0.2.0
+
+- openai>=1.50.0
++ openai>=2.0.0,<3.0.0
+
+- pinecone-client>=5.0.0
++ pinecone-client>=6.0.0
+
+- tiktoken>=0.8.0
++ tiktoken>=0.10.0,<1.0.0
+```
+
+### 2. Added Pyannote Specific Versions
+```python
+pyannote.audio==3.4.0
+pyannote.core==5.0.0
+pyannote.database==5.1.3
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pyannoteai-sdk==0.3.0
+```
+
+### 3. Added PyTorch Audio Processing
+```python
+torch-audiomentations>=0.11.0
+torch_pitch_shift>=1.2.0
+torchmetrics>=1.0.0
+av>=10.0.0
+pydub>=0.25.0
+```
+
+### 4. Added ML/NLP Dependencies (Required by pyannote/whisperx)
+```python
+transformers>=4.30.0
+tokenizers>=0.13.0
+sentencepiece>=0.1.99
+speechbrain>=0.5.0
+pytorch-lightning>=2.0.0
+pytorch-metric-learning>=2.0.0
+einops>=0.6.0
+omegaconf>=2.3.0
+HyperPyYAML>=1.2.0
+asteroid-filterbanks>=0.4.0
+julius>=0.2.0
+onnxruntime>=1.15.0
+protobuf>=4.0.0
+```
+
+## Testing
+After deploying with the updated requirements.txt, the error should be resolved and MCP tools should load successfully.
+
+## Why This Happened
+The original requirements.txt used loose version constraints (e.g., `>=0.3.0` without upper bounds) which allowed pip to install incompatible combinations of packages. The fixed version pins minimum versions that are known to work together from your local environment.

requirements.txt

@@ -14,33 +14,66 @@ websockets>=12.0
 # =================================================================
 whisperx>=3.1.1
 faster-whisper>=1.0.0
-pyannote.audio>=3.1.1
+
+# Pyannote with specific versions (critical for compatibility)
+pyannote.audio==3.4.0
+pyannote.core==5.0.0
+pyannote.database==5.1.3
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pyannoteai-sdk==0.3.0
+
+# PyTorch
 torch>=2.0.0
 torchaudio>=2.0.0
+torch-audiomentations>=0.11.0
+torch_pitch_shift>=1.2.0
+torchmetrics>=1.0.0
+
+# Audio processing
 soundfile>=0.12.0
 ffmpeg-python>=0.2.0
+av>=10.0.0
+pydub>=0.25.0
 
 # =================================================================
 # AGENT & LOGIC (LangChain / LangGraph)
 # =================================================================
-langchain>=0.3.0
-langchain-community>=0.3.0
-langchain-core>=0.3.0
-langchain-openai>=0.3.0
-langchain-pinecone>=0.2.0
-langchain-text-splitters>=0.3.0
-langchain-mcp-adapters>=0.1.0
-langgraph>=0.2.0
-openai>=1.50.0
-pinecone-client>=5.0.0
-tiktoken>=0.8.0
+langchain>=0.3.0,<0.4.0
+langchain-community>=0.3.0,<0.4.0
+langchain-core>=0.3.80,<0.4.0
+langchain-openai>=0.3.0,<0.4.0
+langchain-pinecone>=0.2.0,<0.3.0
+langchain-text-splitters>=0.3.0,<0.4.0
+langchain-mcp-adapters>=0.1.14,<0.2.0
+langgraph>=0.2.0,<0.3.0
+openai>=2.0.0,<3.0.0
+pinecone-client>=6.0.0
+tiktoken>=0.10.0,<1.0.0
 mcp>=1.0.0
 
+# =================================================================
+# ML & NLP DEPENDENCIES (Required by pyannote/whisperx)
+# =================================================================
+transformers>=4.30.0
+tokenizers>=0.13.0
+sentencepiece>=0.1.99
+speechbrain>=0.5.0
+pytorch-lightning>=2.0.0
+pytorch-metric-learning>=2.0.0
+einops>=0.6.0
+omegaconf>=2.3.0
+HyperPyYAML>=1.2.0
+asteroid-filterbanks>=0.4.0
+julius>=0.2.0
+onnxruntime>=1.15.0
+protobuf>=4.0.0
+
 # =================================================================
 # DATA & UTILITIES
 # Removed strict pinnings (like numpy==2.3.5) that don't exist on Docker
 # =================================================================
-numpy>=1.24.0,<2.3.0
+numpy>=1.24.0,<2.4.0
 pandas>=2.0.0
 scipy>=1.10.0
 scikit-learn>=1.3.0
@@ -50,4 +83,4 @@ pytz>=2023.3
 tqdm>=4.66.0
 packaging>=23.0
 pyyaml>=6.0
-regex>=2023.0.0
+regex>=2023.0.0

requirements_comparison.md

@@ -0,0 +1,77 @@
+# Requirements.txt Comparison Analysis
+
+## Critical Missing Dependencies in HF requirements.txt
+
+### 1. **Pyannote Specific Versions** (CRITICAL)
+The HF requirements.txt has `pyannote.audio>=3.1.1` but the working version uses specific pinned versions:
+```
+pyannote.audio==3.4.0
+pyannote.core==5.0.0
+pyannote.database==5.1.3
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pyannoteai-sdk==0.3.0
+```
+
+### 2. **OpenAI Version Mismatch** (CRITICAL)
+- HF: `openai>=1.50.0`
+- Working: `openai>=2.0.0,<3.0.0` (actual: 2.8.1)
+
+### 3. **Pinecone Version Mismatch** (CRITICAL)
+- HF: `pinecone-client>=5.0.0`
+- Working: `pinecone-client>=6.0.0` (actual: 6.0.0)
+
+### 4. **Tiktoken Version Mismatch**
+- HF: `tiktoken>=0.8.0`
+- Working: `tiktoken>=0.10.0,<1.0.0` (actual: 0.12.0)
+
+### 5. **Missing Dependencies** (Not in HF requirements.txt)
+These packages are installed in the working venv but not specified in HF requirements:
+- `lightning==2.5.6`
+- `pytorch-lightning==2.5.6`
+- `pytorch-metric-learning==2.9.0`
+- `speechbrain==1.0.3`
+- `sentencepiece==0.2.1`
+- `transformers==4.57.3`
+- `tokenizers==0.22.1`
+- `tensorboardX==2.6.4`
+- `einops==0.8.1`
+- `omegaconf==2.3.0`
+- `HyperPyYAML==1.2.2`
+- `asteroid-filterbanks==0.4.0`
+- `julius==0.2.7`
+- `onnxruntime==1.23.2`
+- `protobuf==6.33.1`
+- `coloredlogs==15.0.1`
+- `humanfriendly==10.0`
+
+### 6. **Torch Audio Processing Dependencies**
+- `torch-audiomentations==0.12.0`
+- `torch_pitch_shift==1.2.5`
+- `torchcodec==0.7.0`
+- `torchmetrics==1.8.2`
+
+### 7. **Additional Data Processing**
+- `av==15.1.0` (for video processing)
+- `imageio==2.37.2`
+- `imageio-ffmpeg==0.6.0`
+- `moviepy==2.2.1`
+- `pydub==0.25.1`
+
+## Recommendations
+
+### High Priority (MUST FIX)
+1. Pin pyannote versions exactly as in working environment
+2. Update OpenAI to 2.x range
+3. Update Pinecone to 6.x
+4. Add transformers, tokenizers, sentencepiece (likely needed for model loading)
+5. Add speechbrain (likely needed by pyannote)
+
+### Medium Priority (SHOULD ADD)
+1. Add PyTorch ecosystem packages: pytorch-lightning, pytorch-metric-learning, torchmetrics
+2. Add audio processing: torch-audiomentations, torch_pitch_shift, torchcodec
+3. Add video processing: av, moviepy, imageio
+
+### Low Priority (OPTIONAL)
+1. Add logging utilities: coloredlogs, humanfriendly
+2. Add config management: omegaconf, HyperPyYAML