feat: Enhance embedding generation and search capabilities

- Added pre-calculation of estimated chunk count for HNSW capacity in `generate_dense_embeddings_centralized` to optimize indexing performance.
- Implemented binary vector generation with memory-mapped storage for efficient cascade search, including metadata saving.
- Introduced SPLADE sparse index generation with improved handling and metadata storage.
- Updated `ChainSearchEngine` to prefer centralized binary searcher for improved performance and added fallback to legacy binary index.
- Deprecated `BinaryANNIndex` in favor of `BinarySearcher` for better memory management and performance.
- Enhanced `SpladeEncoder` with warmup functionality to reduce latency spikes during first-time inference.
- Improved `SpladeIndex` with cache size adjustments for better query performance.
- Added methods for managing binary vectors in `VectorMetadataStore`, including batch insertion and retrieval.
- Created a new `BinarySearcher` class for efficient binary vector search using Hamming distance, supporting both memory-mapped and database loading modes.

codex-lens/src/codex_lens.egg-info/requires.txt

@@ -6,6 +6,7 @@ tree-sitter-python>=0.25
 tree-sitter-javascript>=0.25
 tree-sitter-typescript>=0.23
 pathspec>=0.11
+watchdog>=3.0
 
 [encoding]
 chardet>=5.0
@@ -13,6 +14,25 @@ chardet>=5.0
 [full]
 tiktoken>=0.5.0
 
+[reranker]
+optimum>=1.16
+onnxruntime>=1.15
+transformers>=4.36
+
+[reranker-api]
+httpx>=0.25
+
+[reranker-legacy]
+sentence-transformers>=2.2
+
+[reranker-litellm]
+ccw-litellm>=0.1
+
+[reranker-onnx]
+optimum>=1.16
+onnxruntime>=1.15
+transformers>=4.36
+
 [semantic]
 numpy>=1.24
 fastembed>=0.2
@@ -29,3 +49,11 @@ numpy>=1.24
 fastembed>=0.2
 hnswlib>=0.8.0
 onnxruntime-gpu>=1.15.0
+
+[splade]
+transformers>=4.36
+optimum[onnxruntime]>=1.16
+
+[splade-gpu]
+transformers>=4.36
+optimum[onnxruntime-gpu]>=1.16