sdca-rag 0.1.0__tar.gz

sdca_rag-0.1.0/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: sdca-rag
+Version: 0.1.0
+Summary: Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation (RAG) Systems
+Author: Subodh Butt, Ashish Dhillon
+License-Expression: MIT
+Keywords: rag,chunking,llm,information-retrieval,document-ai,pdf-parsing,stair
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pymupdf>=1.24.0
+Requires-Dist: sentence-transformers>=2.2.0
+Requires-Dist: faiss-cpu>=1.7.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pandas>=2.0.0
+
+# Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation Systems (SDCA)
+
+## Overview
+This repository implements **SDCA (Structure-Aware Document Chunking Algorithm)**, an M.Tech research project addressing chunk boundary degradation in PDF-based Retrieval-Augmented Generation (RAG) pipelines.
+
+Standard naive chunking strategies (fixed-size windowing, simple character recursive splitting) often cleave paragraphs mid-sentence, ignore section hierarchies, and fragment semantic context, leading to degraded retrieval precision. SDCA provides a deterministic, layout-aware chunking pipeline that leverages PDF typography and document structure extracted via PyMuPDF.
+
+---
+
+## 5-Phase Implementation Plan
+
+1. **Phase 1: PDF Extraction Foundation** (**COMPLETED**)
+   - Extract structured text blocks, bounding boxes, font sizes, flags, and page metadata via PyMuPDF (`fitz`).
+2. **Phase 2: Baseline Chunking** (**COMPLETED**)
+   - Implement three standard RAG chunking baselines: Fixed-Size, Recursive, and Sentence-based Chunking.
+3. **Phase 3: SDCA Proposed Algorithm** (**COMPLETED**)
+   - Implement the deterministic structure-aware chunking algorithm targeting ~400 tokens (range 200–600 tokens) with heading detection, paragraph preservation, and sentence-bounded splitting.
+4. **Phase 4: Retrieval and Controlled Experiments** (**COMPLETED**)
+   - Generate embeddings using Sentence Transformers (`all-MiniLM-L6-v2`) and build FAISS vector indexes (`IndexFlatIP`) under strict *Ceteris Paribus* conditions.
+5. **Phase 5 & 5.1: Evaluation Dashboard & Interactive Research Laboratory** (**COMPLETED**)
+   - Interactive viva research laboratory for visual inspection, multi-algorithm side-by-side chunking, multi-strategy live FAISS retrieval, and frozen official benchmark presentation.
+6. **Phase V2: SDCA V2 Hierarchical Evolution & Controlled 5-Way Benchmark** (**COMPLETED**)
+   - Hierarchical section context (`section_path`), heading-content binding, structure-aware retrieval text (`chunk.retrieval_text`), small-chunk merging, and 5-strategy comparative benchmark.
+
+---
+
+## Running the SDCA Research Laboratory
+
+Launch the interactive Streamlit research laboratory:
+
+```bash
+# Direct run via virtual environment
+.venv/bin/streamlit run src/app/streamlit_app.py
+```
+
+The application opens at `http://localhost:8501` featuring 5 dedicated research views:
+1. **Overview:** Executive product landing page with capability cards and aggregate dataset metrics.
+2. **SDCA Explorer:** Deep visual inspection of both SDCA V1 and SDCA V2 (modal body font inference, hierarchical breadcrumbs, heading binding, and structure-aware retrieval text).
+3. **Algorithm Comparison:** Side-by-side multi-algorithm execution (`Fixed`, `Recursive`, `Sentence`, `SDCA V1`, `SDCA V2`) on the same PDF with token statistics, distribution charts, and sequential position chunk inspection.
+4. **Live Retrieval Lab:** Multi-algorithm semantic search under identical embedding and FAISS conditions with side-by-side cosine similarity scoring and vector text inspection.
+5. **Official Benchmark:** Tabbed evaluation featuring the full 5-way V2 benchmark, the frozen Phase 4 baseline, and direct head-to-head SDCA V1 vs SDCA V2 evolution analysis.
+6. **About SDCA:** Algorithmic pipeline, typography heuristics, and viva examination defense notes.
+
+---
+
+## Running the Automated Test Suite
+
+Execute the full 100-test automated test suite across all project phases:
+
+```bash
+.venv/bin/pytest -v tests/
+```
+
+Expected result: `100 passed, 0 failures` (100% pass rate).
+
+
+---
+
+## Research Controls (*Ceteris Paribus*)
+To ensure scientific validity, all retrieval benchmarks hold constant:
+- Document corpus (3 landmark academic papers: Attention, RAG, BERT; 50 pages total)
+- Benchmark query set & ground truth (15 verified technical queries)
+- Embedding model (`sentence-transformers/all-MiniLM-L6-v2`, 384 dimensions)
+- Subword tokenizer (injected model tokenizer across all 4 chunkers)
+- Vector index algorithm (FAISS `IndexFlatIP`)
+- Similarity metric (Exact Cosine Similarity via unit $L_2$-normalized inner product)
+- Retrieval depth ($K = 5$)
+- Evaluation metrics (Precision@5, Recall@5, Hit Rate@5, MRR, NDCG@5)
+
+*The only independent variable is the chunking algorithm.*
+
+---
+
+## Technical Documentation
+- [docs/SDCA_ALGORITHM.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/SDCA_ALGORITHM.md): Algorithmic specification, pseudocode, and typography heuristics.
+- [docs/EXPERIMENT_PROTOCOL.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/EXPERIMENT_PROTOCOL.md): 19-point formal controlled retrieval experiment protocol.
+- [docs/PHASE5_DASHBOARD.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/PHASE5_DASHBOARD.md): Demonstration dashboard architecture and viva defense guide.
+
+---
+
+## Governance Documents
+- [RULES.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/RULES.md): Research rules, algorithmic boundaries, and coding standards.
+- [PROJECT_STATE.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/PROJECT_STATE.md): Current phase, deliverable tracker, and experiment states.
+- [DECISIONS.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/DECISIONS.md): Architectural Decision Records (ADRs).
+- [ERROR_CHANGE_LOG.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/ERROR_CHANGE_LOG.md): Historical log of errors, refactorings, and changes.

sdca_rag-0.1.0/README.md

@@ -0,0 +1,85 @@
+# Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation Systems (SDCA)
+
+## Overview
+This repository implements **SDCA (Structure-Aware Document Chunking Algorithm)**, an M.Tech research project addressing chunk boundary degradation in PDF-based Retrieval-Augmented Generation (RAG) pipelines.
+
+Standard naive chunking strategies (fixed-size windowing, simple character recursive splitting) often cleave paragraphs mid-sentence, ignore section hierarchies, and fragment semantic context, leading to degraded retrieval precision. SDCA provides a deterministic, layout-aware chunking pipeline that leverages PDF typography and document structure extracted via PyMuPDF.
+
+---
+
+## 5-Phase Implementation Plan
+
+1. **Phase 1: PDF Extraction Foundation** (**COMPLETED**)
+   - Extract structured text blocks, bounding boxes, font sizes, flags, and page metadata via PyMuPDF (`fitz`).
+2. **Phase 2: Baseline Chunking** (**COMPLETED**)
+   - Implement three standard RAG chunking baselines: Fixed-Size, Recursive, and Sentence-based Chunking.
+3. **Phase 3: SDCA Proposed Algorithm** (**COMPLETED**)
+   - Implement the deterministic structure-aware chunking algorithm targeting ~400 tokens (range 200–600 tokens) with heading detection, paragraph preservation, and sentence-bounded splitting.
+4. **Phase 4: Retrieval and Controlled Experiments** (**COMPLETED**)
+   - Generate embeddings using Sentence Transformers (`all-MiniLM-L6-v2`) and build FAISS vector indexes (`IndexFlatIP`) under strict *Ceteris Paribus* conditions.
+5. **Phase 5 & 5.1: Evaluation Dashboard & Interactive Research Laboratory** (**COMPLETED**)
+   - Interactive viva research laboratory for visual inspection, multi-algorithm side-by-side chunking, multi-strategy live FAISS retrieval, and frozen official benchmark presentation.
+6. **Phase V2: SDCA V2 Hierarchical Evolution & Controlled 5-Way Benchmark** (**COMPLETED**)
+   - Hierarchical section context (`section_path`), heading-content binding, structure-aware retrieval text (`chunk.retrieval_text`), small-chunk merging, and 5-strategy comparative benchmark.
+
+---
+
+## Running the SDCA Research Laboratory
+
+Launch the interactive Streamlit research laboratory:
+
+```bash
+# Direct run via virtual environment
+.venv/bin/streamlit run src/app/streamlit_app.py
+```
+
+The application opens at `http://localhost:8501` featuring 5 dedicated research views:
+1. **Overview:** Executive product landing page with capability cards and aggregate dataset metrics.
+2. **SDCA Explorer:** Deep visual inspection of both SDCA V1 and SDCA V2 (modal body font inference, hierarchical breadcrumbs, heading binding, and structure-aware retrieval text).
+3. **Algorithm Comparison:** Side-by-side multi-algorithm execution (`Fixed`, `Recursive`, `Sentence`, `SDCA V1`, `SDCA V2`) on the same PDF with token statistics, distribution charts, and sequential position chunk inspection.
+4. **Live Retrieval Lab:** Multi-algorithm semantic search under identical embedding and FAISS conditions with side-by-side cosine similarity scoring and vector text inspection.
+5. **Official Benchmark:** Tabbed evaluation featuring the full 5-way V2 benchmark, the frozen Phase 4 baseline, and direct head-to-head SDCA V1 vs SDCA V2 evolution analysis.
+6. **About SDCA:** Algorithmic pipeline, typography heuristics, and viva examination defense notes.
+
+---
+
+## Running the Automated Test Suite
+
+Execute the full 100-test automated test suite across all project phases:
+
+```bash
+.venv/bin/pytest -v tests/
+```
+
+Expected result: `100 passed, 0 failures` (100% pass rate).
+
+
+---
+
+## Research Controls (*Ceteris Paribus*)
+To ensure scientific validity, all retrieval benchmarks hold constant:
+- Document corpus (3 landmark academic papers: Attention, RAG, BERT; 50 pages total)
+- Benchmark query set & ground truth (15 verified technical queries)
+- Embedding model (`sentence-transformers/all-MiniLM-L6-v2`, 384 dimensions)
+- Subword tokenizer (injected model tokenizer across all 4 chunkers)
+- Vector index algorithm (FAISS `IndexFlatIP`)
+- Similarity metric (Exact Cosine Similarity via unit $L_2$-normalized inner product)
+- Retrieval depth ($K = 5$)
+- Evaluation metrics (Precision@5, Recall@5, Hit Rate@5, MRR, NDCG@5)
+
+*The only independent variable is the chunking algorithm.*
+
+---
+
+## Technical Documentation
+- [docs/SDCA_ALGORITHM.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/SDCA_ALGORITHM.md): Algorithmic specification, pseudocode, and typography heuristics.
+- [docs/EXPERIMENT_PROTOCOL.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/EXPERIMENT_PROTOCOL.md): 19-point formal controlled retrieval experiment protocol.
+- [docs/PHASE5_DASHBOARD.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/PHASE5_DASHBOARD.md): Demonstration dashboard architecture and viva defense guide.
+
+---
+
+## Governance Documents
+- [RULES.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/RULES.md): Research rules, algorithmic boundaries, and coding standards.
+- [PROJECT_STATE.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/PROJECT_STATE.md): Current phase, deliverable tracker, and experiment states.
+- [DECISIONS.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/DECISIONS.md): Architectural Decision Records (ADRs).
+- [ERROR_CHANGE_LOG.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/ERROR_CHANGE_LOG.md): Historical log of errors, refactorings, and changes.

sdca_rag-0.1.0/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sdca-rag"
+version = "0.1.0"
+authors = [
+    { name = "Subodh Butt" },
+    { name = "Ashish Dhillon" }
+]
+description = "Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation (RAG) Systems"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+keywords = ["rag", "chunking", "llm", "information-retrieval", "document-ai", "pdf-parsing", "stair"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "pymupdf>=1.24.0",
+    "sentence-transformers>=2.2.0",
+    "faiss-cpu>=1.7.0",
+    "numpy>=1.24.0",
+    "pandas>=2.0.0"
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["src*", "sdca*"]

sdca_rag-0.1.0/sdca/__init__.py

@@ -0,0 +1,60 @@
+"""SDCA: Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation (RAG) Systems.
+
+Developed by Subodh Butt & Ashish Dhillon.
+"""
+
+from src.baselines.models import Chunk
+from src.extraction.models import Document
+from src.extraction.pdf_parser import load_pdf
+from src.retrieval.hybrid import BM25, rrf, structure_guided_rrf
+from src.sdca.chunker import chunk_sdca
+from src.sdca.v2.chunker import chunk_sdca_v2
+from src.sdca.v3.chunker import V3Options, chunk_sdca_stair, chunk_sdca_v3
+
+__version__ = "0.1.0"
+__all__ = [
+    "chunk_document",
+    "load_pdf",
+    "chunk_sdca_stair",
+    "chunk_sdca_v2",
+    "chunk_sdca",
+    "structure_guided_rrf",
+    "SDCATextSplitter",
+    "Chunk",
+    "Document",
+    "V3Options",
+]
+
+
+def chunk_document(pdf_path: str, target_tokens: int = 300, **kwargs):
+    """High-level convenience API to load and chunk any PDF using the champion SDCA algorithm.
+    
+    Args:
+        pdf_path: Path to the target PDF document.
+        target_tokens: Desired target token size per chunk (default: 300).
+        
+    Returns:
+        List of layout-aware Chunk objects.
+    """
+    doc = load_pdf(pdf_path)
+    return chunk_sdca_stair(doc, target_tokens=target_tokens, **kwargs)
+
+
+class SDCATextSplitter:
+    """Drop-in LangChain-compatible Document Transformer for SDCA."""
+
+    def __init__(self, target_tokens: int = 300, min_tokens: int = 120, max_tokens: int = 420, **kwargs):
+        self.target_tokens = target_tokens
+        self.min_tokens = min_tokens
+        self.max_tokens = max_tokens
+        self.kwargs = kwargs
+
+    def split_pdf(self, pdf_path: str):
+        """Chunks a PDF document preserving section hierarchies and tables."""
+        return chunk_document(
+            pdf_path,
+            target_tokens=self.target_tokens,
+            min_tokens=self.min_tokens,
+            max_tokens=self.max_tokens,
+            **self.kwargs,
+        )

sdca_rag-0.1.0/sdca_rag.egg-info/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: sdca-rag
+Version: 0.1.0
+Summary: Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation (RAG) Systems
+Author: Subodh Butt, Ashish Dhillon
+License-Expression: MIT
+Keywords: rag,chunking,llm,information-retrieval,document-ai,pdf-parsing,stair
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pymupdf>=1.24.0
+Requires-Dist: sentence-transformers>=2.2.0
+Requires-Dist: faiss-cpu>=1.7.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pandas>=2.0.0
+
+# Structure-Aware Document Chunking Algorithm for Retrieval-Augmented Generation Systems (SDCA)
+
+## Overview
+This repository implements **SDCA (Structure-Aware Document Chunking Algorithm)**, an M.Tech research project addressing chunk boundary degradation in PDF-based Retrieval-Augmented Generation (RAG) pipelines.
+
+Standard naive chunking strategies (fixed-size windowing, simple character recursive splitting) often cleave paragraphs mid-sentence, ignore section hierarchies, and fragment semantic context, leading to degraded retrieval precision. SDCA provides a deterministic, layout-aware chunking pipeline that leverages PDF typography and document structure extracted via PyMuPDF.
+
+---
+
+## 5-Phase Implementation Plan
+
+1. **Phase 1: PDF Extraction Foundation** (**COMPLETED**)
+   - Extract structured text blocks, bounding boxes, font sizes, flags, and page metadata via PyMuPDF (`fitz`).
+2. **Phase 2: Baseline Chunking** (**COMPLETED**)
+   - Implement three standard RAG chunking baselines: Fixed-Size, Recursive, and Sentence-based Chunking.
+3. **Phase 3: SDCA Proposed Algorithm** (**COMPLETED**)
+   - Implement the deterministic structure-aware chunking algorithm targeting ~400 tokens (range 200–600 tokens) with heading detection, paragraph preservation, and sentence-bounded splitting.
+4. **Phase 4: Retrieval and Controlled Experiments** (**COMPLETED**)
+   - Generate embeddings using Sentence Transformers (`all-MiniLM-L6-v2`) and build FAISS vector indexes (`IndexFlatIP`) under strict *Ceteris Paribus* conditions.
+5. **Phase 5 & 5.1: Evaluation Dashboard & Interactive Research Laboratory** (**COMPLETED**)
+   - Interactive viva research laboratory for visual inspection, multi-algorithm side-by-side chunking, multi-strategy live FAISS retrieval, and frozen official benchmark presentation.
+6. **Phase V2: SDCA V2 Hierarchical Evolution & Controlled 5-Way Benchmark** (**COMPLETED**)
+   - Hierarchical section context (`section_path`), heading-content binding, structure-aware retrieval text (`chunk.retrieval_text`), small-chunk merging, and 5-strategy comparative benchmark.
+
+---
+
+## Running the SDCA Research Laboratory
+
+Launch the interactive Streamlit research laboratory:
+
+```bash
+# Direct run via virtual environment
+.venv/bin/streamlit run src/app/streamlit_app.py
+```
+
+The application opens at `http://localhost:8501` featuring 5 dedicated research views:
+1. **Overview:** Executive product landing page with capability cards and aggregate dataset metrics.
+2. **SDCA Explorer:** Deep visual inspection of both SDCA V1 and SDCA V2 (modal body font inference, hierarchical breadcrumbs, heading binding, and structure-aware retrieval text).
+3. **Algorithm Comparison:** Side-by-side multi-algorithm execution (`Fixed`, `Recursive`, `Sentence`, `SDCA V1`, `SDCA V2`) on the same PDF with token statistics, distribution charts, and sequential position chunk inspection.
+4. **Live Retrieval Lab:** Multi-algorithm semantic search under identical embedding and FAISS conditions with side-by-side cosine similarity scoring and vector text inspection.
+5. **Official Benchmark:** Tabbed evaluation featuring the full 5-way V2 benchmark, the frozen Phase 4 baseline, and direct head-to-head SDCA V1 vs SDCA V2 evolution analysis.
+6. **About SDCA:** Algorithmic pipeline, typography heuristics, and viva examination defense notes.
+
+---
+
+## Running the Automated Test Suite
+
+Execute the full 100-test automated test suite across all project phases:
+
+```bash
+.venv/bin/pytest -v tests/
+```
+
+Expected result: `100 passed, 0 failures` (100% pass rate).
+
+
+---
+
+## Research Controls (*Ceteris Paribus*)
+To ensure scientific validity, all retrieval benchmarks hold constant:
+- Document corpus (3 landmark academic papers: Attention, RAG, BERT; 50 pages total)
+- Benchmark query set & ground truth (15 verified technical queries)
+- Embedding model (`sentence-transformers/all-MiniLM-L6-v2`, 384 dimensions)
+- Subword tokenizer (injected model tokenizer across all 4 chunkers)
+- Vector index algorithm (FAISS `IndexFlatIP`)
+- Similarity metric (Exact Cosine Similarity via unit $L_2$-normalized inner product)
+- Retrieval depth ($K = 5$)
+- Evaluation metrics (Precision@5, Recall@5, Hit Rate@5, MRR, NDCG@5)
+
+*The only independent variable is the chunking algorithm.*
+
+---
+
+## Technical Documentation
+- [docs/SDCA_ALGORITHM.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/SDCA_ALGORITHM.md): Algorithmic specification, pseudocode, and typography heuristics.
+- [docs/EXPERIMENT_PROTOCOL.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/EXPERIMENT_PROTOCOL.md): 19-point formal controlled retrieval experiment protocol.
+- [docs/PHASE5_DASHBOARD.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/docs/PHASE5_DASHBOARD.md): Demonstration dashboard architecture and viva defense guide.
+
+---
+
+## Governance Documents
+- [RULES.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/RULES.md): Research rules, algorithmic boundaries, and coding standards.
+- [PROJECT_STATE.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/PROJECT_STATE.md): Current phase, deliverable tracker, and experiment states.
+- [DECISIONS.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/DECISIONS.md): Architectural Decision Records (ADRs).
+- [ERROR_CHANGE_LOG.md](file:///Users/ashishdhillon/DPG/Coordinator/Mtech%20Synopsis/SDCA%20PRoject/Project/ERROR_CHANGE_LOG.md): Historical log of errors, refactorings, and changes.

sdca_rag-0.1.0/sdca_rag.egg-info/SOURCES.txt

@@ -0,0 +1,47 @@
+README.md
+pyproject.toml
+sdca/__init__.py
+sdca_rag.egg-info/PKG-INFO
+sdca_rag.egg-info/SOURCES.txt
+sdca_rag.egg-info/dependency_links.txt
+sdca_rag.egg-info/requires.txt
+sdca_rag.egg-info/top_level.txt
+src/__init__.py
+src/app/__init__.py
+src/app/comparison.py
+src/app/streamlit_app.py
+src/baselines/__init__.py
+src/baselines/fixed.py
+src/baselines/models.py
+src/baselines/recursive.py
+src/baselines/sentence.py
+src/baselines/tokenization.py
+src/evaluation/__init__.py
+src/experiments/__init__.py
+src/experiments/metrics.py
+src/experiments/runner.py
+src/experiments/runner_v2.py
+src/extraction/__init__.py
+src/extraction/models.py
+src/extraction/pdf_parser.py
+src/retrieval/__init__.py
+src/retrieval/embeddings.py
+src/retrieval/faiss_store.py
+src/retrieval/hybrid.py
+src/sdca/__init__.py
+src/sdca/chunker.py
+src/sdca/structure.py
+src/sdca/v2/__init__.py
+src/sdca/v2/chunker.py
+src/sdca/v2/structure.py
+src/sdca/v3/__init__.py
+src/sdca/v3/chunker.py
+tests/test_app.py
+tests/test_baselines.py
+tests/test_experiments.py
+tests/test_extraction.py
+tests/test_qasper_pdf_eval.py
+tests/test_retrieval.py
+tests/test_sdca.py
+tests/test_sdca_v2.py
+tests/test_sdca_v3.py

sdca_rag-0.1.0/sdca_rag.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

sdca_rag-0.1.0/sdca_rag.egg-info/requires.txt

@@ -0,0 +1,5 @@
+pymupdf>=1.24.0
+sentence-transformers>=2.2.0
+faiss-cpu>=1.7.0
+numpy>=1.24.0
+pandas>=2.0.0

sdca_rag-0.1.0/sdca_rag.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+sdca
+src

sdca_rag-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sdca_rag-0.1.0/src/__init__.py

@@ -0,0 +1,6 @@
+"""SDCA Research Project Source Package."""
+
+import os
+
+# Prevent OpenMP runtime conflict between faiss-cpu and torch on macOS
+os.environ.setdefault("KMP_DUPLICATE_LIB_OK", "TRUE")

sdca_rag-0.1.0/src/app/__init__.py

@@ -0,0 +1 @@
+"""Streamlit Demonstration and Evaluation Dashboard Package for SDCA."""