corp-extractor 0.4.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

{corp_extractor-0.4.0.dist-info → corp_extractor-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: corp-extractor
-Version: 0.4.0
+Version: 0.9.0
 Summary: Extract structured statements from text using T5-Gemma 2 and Diverse Beam Search
 Project-URL: Homepage, https://github.com/corp-o-rate/statement-extractor
 Project-URL: Documentation, https://github.com/corp-o-rate/statement-extractor#readme
@@ -23,18 +23,35 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Text Processing :: Linguistic
 Requires-Python: >=3.10
+Requires-Dist: accelerate>=1.12.0
+Requires-Dist: beautifulsoup4>=4.12.0
 Requires-Dist: click>=8.0.0
+Requires-Dist: gguf>=0.17.1
 Requires-Dist: gliner2
+Requires-Dist: httpx>=0.25.0
+Requires-Dist: huggingface-hub>=0.20.0
+Requires-Dist: llama-cpp-python>=0.3.16
 Requires-Dist: numpy>=1.24.0
 Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pymupdf>=1.23.0
 Requires-Dist: sentence-transformers>=2.2.0
+Requires-Dist: sqlite-vec>=0.1.6
 Requires-Dist: torch>=2.0.0
 Requires-Dist: transformers>=5.0.0rc3
+Provides-Extra: all
+Requires-Dist: llama-cpp-python>=0.2.0; extra == 'all'
+Requires-Dist: pillow>=10.0.0; extra == 'all'
+Requires-Dist: pytesseract>=0.3.10; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: llm
+Requires-Dist: llama-cpp-python>=0.2.0; extra == 'llm'
+Provides-Extra: ocr
+Requires-Dist: pillow>=10.0.0; extra == 'ocr'
+Requires-Dist: pytesseract>=0.3.10; extra == 'ocr'
 Description-Content-Type: text/markdown
 
 # Corp Extractor
@@ -47,21 +64,20 @@ Extract structured subject-predicate-object statements from unstructured text us
 
 ## Features
 
+- **Person Database** *(v0.9.0)*: Qualify notable people (executives, politicians, athletes, etc.) against Wikidata with canonical IDs
+- **5-Stage Pipeline** *(v0.8.0)*: Modular plugin-based architecture for full entity resolution
+- **Document Processing** *(v0.7.0)*: Process documents, URLs, and PDFs with chunking and deduplication
+- **Entity Embedding Database** *(v0.6.0)*: Fast entity qualification using vector similarity (~100K+ SEC, ~3M GLEIF, ~5M UK organizations)
 - **Structured Extraction**: Converts unstructured text into subject-predicate-object triples
 - **Entity Type Recognition**: Identifies 12 entity types (ORG, PERSON, GPE, LOC, PRODUCT, EVENT, etc.)
+- **Entity Qualification** *(v0.8.0)*: Adds identifiers (LEI, ticker, company numbers), canonical names, and FQN via embedding database
+- **Statement Labeling** *(v0.5.0)*: Sentiment analysis, relation type classification, confidence scoring
 - **GLiNER2 Integration** *(v0.4.0)*: Uses GLiNER2 (205M params) for entity recognition and relation extraction
-- **Predefined Predicates** *(v0.4.0)*: Optional `--predicates` list for GLiNER2 relation extraction mode
-- **Entity-based Scoring** *(v0.4.0)*: Confidence combines semantic similarity (50%) + entity recognition scores (25% each)
-- **Multi-Candidate Extraction**: Generates 3 candidates per statement (hybrid, GLiNER2-only, predicate-split)
-- **Best Triple Selection**: Keeps only highest-scoring triple per source (use `--all-triples` to keep all)
-- **Extraction Method Tracking**: Each statement includes `extraction_method` field (hybrid, gliner, split, model)
+- **Predefined Predicates**: Optional `--predicates` list for GLiNER2 relation extraction mode
 - **Beam Merging**: Combines top beams for better coverage instead of picking one
 - **Embedding-based Dedup**: Uses semantic similarity to detect near-duplicate predicates
 - **Predicate Taxonomies**: Normalize predicates to canonical forms via embeddings
-- **Contextualized Matching**: Compares full "Subject Predicate Object" against source text for better accuracy
-- **Entity Type Merging**: Automatically merges UNKNOWN entity types with specific types during deduplication
-- **Reversal Detection**: Detects and corrects subject-object reversals using embedding comparison
-- **Command Line Interface**: Full-featured CLI for terminal usage
+- **Command Line Interface**: Full-featured CLI with `split`, `pipeline`, `document`, and `db` commands
 - **Multiple Output Formats**: Get results as Pydantic models, JSON, XML, or dictionaries
 
 ## Installation
@@ -135,63 +151,74 @@ uvx corp-extractor "Apple announced a new iPhone."
 
 ### Usage Examples
 
-```bash
-# Extract from text argument
-corp-extractor "Apple Inc. announced the iPhone 15 at their September event."
-
-# Extract from file
-corp-extractor -f article.txt
+The CLI provides three main commands: `split`, `pipeline`, and `plugins`.
 
-# Pipe from stdin
-cat article.txt | corp-extractor -
+```bash
+# Simple extraction (Stage 1 only, fast)
+corp-extractor split "Apple Inc. announced the iPhone 15."
+corp-extractor split -f article.txt --json
+
+# Full 5-stage pipeline (entity resolution, labeling, taxonomy)
+corp-extractor pipeline "Amazon CEO Andy Jassy announced plans to hire workers."
+corp-extractor pipeline -f article.txt --stages 1-3
+corp-extractor pipeline "..." --disable-plugins sec_edgar
+
+# Plugin management
+corp-extractor plugins list
+corp-extractor plugins list --stage 3
+corp-extractor plugins info gleif_qualifier
+```
 
-# Output as JSON
-corp-extractor "Tim Cook is CEO of Apple." --json
+### Split Command (Simple Extraction)
 
-# Output as XML
-corp-extractor -f article.txt --xml
+```bash
+corp-extractor split "Tim Cook is CEO of Apple." --json
+corp-extractor split -f article.txt --beams 8 --verbose
+cat article.txt | corp-extractor split -
+```
 
-# Verbose output with confidence scores
-corp-extractor -f article.txt --verbose
+### Pipeline Command (Full Entity Resolution)
 
-# Use more beams for better quality
-corp-extractor -f article.txt --beams 8
+```bash
+# Run all 5 stages
+corp-extractor pipeline "Apple CEO Tim Cook announced..."
 
-# Use custom predicate taxonomy
-corp-extractor -f article.txt --taxonomy predicates.txt
+# Run specific stages
+corp-extractor pipeline "..." --stages 1-3         # Stages 1, 2, 3
+corp-extractor pipeline "..." --stages 1,2,5       # Stages 1, 2, 5
+corp-extractor pipeline "..." --skip-stages 4,5    # Skip stages 4 and 5
 
-# Use GPU explicitly
-corp-extractor -f article.txt --device cuda
+# Plugin selection
+corp-extractor pipeline "..." --plugins gleif,companies_house
+corp-extractor pipeline "..." --disable-plugins sec_edgar
 ```
 
-### CLI Options
+### CLI Reference
 
 ```
-Usage: corp-extractor [OPTIONS] [TEXT]
+Usage: corp-extractor [COMMAND] [OPTIONS]
 
-Options:
+Commands:
+  split      Simple extraction (T5-Gemma only)
+  pipeline   Full 5-stage pipeline with entity resolution
+  plugins    List or inspect available plugins
+
+Split Options:
   -f, --file PATH              Read input from file
   -o, --output [table|json|xml] Output format (default: table)
-  --json                       Output as JSON (shortcut)
-  --xml                        Output as XML (shortcut)
+  --json / --xml               Output format shortcuts
   -b, --beams INTEGER          Number of beams (default: 4)
-  --diversity FLOAT            Diversity penalty (default: 1.0)
-  --max-tokens INTEGER         Max tokens to generate (default: 2048)
-  --no-dedup                   Disable deduplication
-  --no-embeddings              Disable embedding-based dedup (faster)
-  --no-merge                   Disable beam merging
-  --no-gliner                  Disable GLiNER2 extraction (use raw model output)
-  --predicates TEXT            Comma-separated predicate types for GLiNER2 relation extraction
-  --all-triples                Keep all candidate triples (default: best per source)
-  --dedup-threshold FLOAT      Deduplication threshold (default: 0.65)
-  --min-confidence FLOAT       Min confidence filter (default: 0)
-  --taxonomy PATH              Load predicate taxonomy from file
-  --taxonomy-threshold FLOAT   Taxonomy matching threshold (default: 0.5)
+  --no-gliner                  Disable GLiNER2 extraction
+  --predicates TEXT            Comma-separated predicates for relation extraction
   --device [auto|cuda|mps|cpu] Device to use (default: auto)
   -v, --verbose                Show confidence scores and metadata
-  -q, --quiet                  Suppress progress messages
-  --version                    Show version
-  --help                       Show this message
+
+Pipeline Options:
+  --stages TEXT                Stages to run (e.g., '1-3' or '1,2,5')
+  --skip-stages TEXT           Stages to skip (e.g., '4,5')
+  --plugins TEXT               Enable only these plugins (comma-separated)
+  --disable-plugins TEXT       Disable these plugins (comma-separated)
+  -o, --output [table|json|yaml|triples]  Output format
 ```
 
 ## New in v0.2.0: Quality Scoring & Beam Merging
@@ -285,6 +312,237 @@ for stmt in fixed_statements:
 
 During deduplication, reversed duplicates (e.g., "A -> P -> B" and "B -> P -> A") are now detected and merged, with the correct orientation determined by source text similarity.
 
+## Pipeline Architecture
+
+The library uses a **5-stage plugin-based pipeline** for comprehensive entity resolution, statement enrichment, and taxonomy classification.
+
+### Pipeline Stages
+
+| Stage | Name | Input | Output | Key Tech |
+|-------|------|-------|--------|----------|
+| 1 | Splitting | Text | `RawTriple[]` | T5-Gemma2 |
+| 2 | Extraction | `RawTriple[]` | `PipelineStatement[]` | GLiNER2 |
+| 3 | Qualification | Entities | `CanonicalEntity[]` | Embedding DB |
+| 4 | Labeling | Statements | `LabeledStatement[]` | Sentiment, etc. |
+| 5 | Taxonomy | Statements | `TaxonomyResult[]` | MNLI, Embeddings |
+
+### Pipeline Python API
+
+```python
+from statement_extractor.pipeline import ExtractionPipeline, PipelineConfig
+
+# Run full pipeline
+pipeline = ExtractionPipeline()
+ctx = pipeline.process("Amazon CEO Andy Jassy announced plans to hire workers.")
+
+# Access results at each stage
+print(f"Raw triples: {len(ctx.raw_triples)}")
+print(f"Statements: {len(ctx.statements)}")
+print(f"Labeled: {len(ctx.labeled_statements)}")
+
+# Output with fully qualified names
+for stmt in ctx.labeled_statements:
+    print(f"{stmt.subject_fqn} --[{stmt.statement.predicate}]--> {stmt.object_fqn}")
+    # e.g., "Andy Jassy (CEO, Amazon) --[announced]--> plans to hire workers"
+```
+
+### Pipeline Configuration
+
+```python
+from statement_extractor.pipeline import PipelineConfig, ExtractionPipeline
+
+# Run only specific stages
+config = PipelineConfig(
+    enabled_stages={1, 2, 3},  # Skip labeling and taxonomy
+    disabled_plugins={"person_qualifier"},  # Disable specific plugins
+)
+pipeline = ExtractionPipeline(config)
+ctx = pipeline.process(text)
+
+# Alternative: create config from stage string
+config = PipelineConfig.from_stage_string("1-3")  # Stages 1, 2, 3
+```
+
+### Built-in Plugins
+
+**Splitters (Stage 1):**
+- `t5_gemma_splitter` - T5-Gemma2 statement extraction
+
+**Extractors (Stage 2):**
+- `gliner2_extractor` - GLiNER2 entity recognition and relation extraction
+
+**Qualifiers (Stage 3):**
+- `person_qualifier` - PERSON → role, org, canonical ID via Wikidata person database *(enhanced in v0.9.0)*
+- `embedding_company_qualifier` - ORG → canonical name, identifiers (LEI, CIK, company number), and FQN via embedding database
+
+**Labelers (Stage 4):**
+- `sentiment_labeler` - Statement sentiment analysis
+- `confidence_labeler` - Confidence scoring
+- `relation_type_labeler` - Relation type classification
+
+**Taxonomy Classifiers (Stage 5):**
+- `mnli_taxonomy_classifier` - MNLI zero-shot classification against ESG taxonomy
+- `embedding_taxonomy_classifier` - Embedding similarity-based taxonomy classification
+
+Taxonomy classifiers return **multiple labels** per statement above the confidence threshold.
+
+## New in v0.6.0: Entity Embedding Database
+
+v0.6.0 introduces an **entity embedding database** for fast entity qualification using vector similarity search.
+
+### Data Sources
+
+**Organizations:**
+
+| Source | Records | Identifier | EntityType Mapping |
+|--------|---------|------------|-------------------|
+| GLEIF | ~3.2M | LEI (Legal Entity Identifier) | GENERAL→business, FUND→fund, BRANCH→branch, INTERNATIONAL_ORGANIZATION→international_org |
+| SEC Edgar | ~100K+ | CIK (Central Index Key) | business (or fund via SIC codes) |
+| Companies House | ~5M | UK Company Number | Maps company_type to business/nonprofit |
+| Wikidata | Variable | Wikidata QID | 35+ query types mapped to EntityType |
+
+**People** *(v0.9.0)*:
+
+| Source | Records | Identifier | PersonType Classification |
+|--------|---------|------------|--------------------------|
+| Wikidata | Variable | Wikidata QID | executive, politician, athlete, artist, academic, scientist, journalist, entrepreneur, activist |
+
+### EntityType Classification
+
+Each organization record is classified with an `entity_type` field:
+
+| Category | Types |
+|----------|-------|
+| Business | `business`, `fund`, `branch` |
+| Non-profit | `nonprofit`, `ngo`, `foundation`, `trade_union` |
+| Government | `government`, `international_org`, `political_party` |
+| Other | `educational`, `research`, `healthcare`, `media`, `sports`, `religious`, `unknown` |
+
+### Building the Database
+
+```bash
+# Import organizations from authoritative sources
+corp-extractor db import-gleif --download
+corp-extractor db import-sec --download      # Bulk submissions.zip (~100K+ filers)
+corp-extractor db import-companies-house --download
+corp-extractor db import-wikidata --limit 50000
+
+# Import notable people (v0.9.0)
+corp-extractor db import-people --type executive --limit 5000
+corp-extractor db import-people --all --limit 10000  # All person types
+
+# Check status
+corp-extractor db status
+
+# Search for an organization
+corp-extractor db search "Microsoft"
+
+# Search for a person (v0.9.0)
+corp-extractor db search-people "Tim Cook"
+```
+
+### Using in Pipeline
+
+The database is automatically used by the `embedding_company_qualifier` plugin for Stage 3 (Qualification):
+
+```python
+from statement_extractor.pipeline import ExtractionPipeline
+
+pipeline = ExtractionPipeline()
+ctx = pipeline.process("Microsoft acquired Activision Blizzard.")
+
+for stmt in ctx.labeled_statements:
+    print(f"{stmt.subject_fqn}")  # e.g., "Microsoft (sec_edgar:0000789019)"
+```
+
+### Publishing to HuggingFace
+
+```bash
+# Upload database with all variants (full, lite, compressed)
+export HF_TOKEN="hf_..."
+corp-extractor db upload                     # Uses default cache location
+corp-extractor db upload entities.db         # Or specify path
+corp-extractor db upload --no-lite           # Skip lite version
+corp-extractor db upload --no-compress       # Skip compressed versions
+
+# Download pre-built database (lite version by default)
+corp-extractor db download                   # Lite version (smaller, faster)
+corp-extractor db download --full            # Full version with all metadata
+
+# Local database management
+corp-extractor db create-lite entities.db    # Create lite version
+corp-extractor db compress entities.db       # Compress with gzip
+```
+
+See [COMPANY_DB.md](../COMPANY_DB.md) for complete build and publish instructions.
+
+## New in v0.7.0: Document Processing
+
+v0.7.0 introduces **document-level processing** for handling files, URLs, and PDFs with automatic chunking, deduplication, and citation tracking.
+
+### Document CLI
+
+```bash
+# Process local files
+corp-extractor document process article.txt
+corp-extractor document process report.txt --title "Annual Report" --year 2024
+
+# Process URLs (web pages and PDFs)
+corp-extractor document process https://example.com/article
+corp-extractor document process https://example.com/report.pdf --use-ocr
+
+# Configure chunking
+corp-extractor document process article.txt --max-tokens 500 --overlap 50
+
+# Preview chunking without extraction
+corp-extractor document chunk article.txt --max-tokens 500
+```
+
+### Document Python API
+
+```python
+from statement_extractor.document import DocumentPipeline, DocumentPipelineConfig, Document
+from statement_extractor.models.document import ChunkingConfig
+
+# Configure document processing
+config = DocumentPipelineConfig(
+    chunking=ChunkingConfig(target_tokens=1000, overlap_tokens=100),
+    generate_summary=True,
+    deduplicate_across_chunks=True,
+)
+
+pipeline = DocumentPipeline(config)
+
+# Process text
+document = Document.from_text("Your long document text...", title="My Document")
+ctx = pipeline.process(document)
+
+# Process URL (async)
+ctx = await pipeline.process_url("https://example.com/article")
+
+# Access results
+print(f"Chunks: {ctx.chunk_count}")
+print(f"Statements: {ctx.statement_count}")
+print(f"Duplicates removed: {ctx.duplicates_removed}")
+
+for stmt in ctx.labeled_statements:
+    print(f"{stmt.subject_fqn} --[{stmt.statement.predicate}]--> {stmt.object_fqn}")
+    if stmt.citation:
+        print(f"  Citation: {stmt.citation}")
+```
+
+### PDF Processing
+
+PDFs are automatically parsed using PyMuPDF. For scanned PDFs, use OCR:
+
+```bash
+# Install OCR dependencies
+pip install "corp-extractor[ocr]"
+
+# Process with OCR
+corp-extractor document process scanned.pdf --use-ocr
+```
+
 ## New in v0.4.0: GLiNER2 Integration
 
 v0.4.0 replaces spaCy with **GLiNER2** (205M params) for entity recognition and relation extraction. GLiNER2 is a unified model that handles NER, text classification, structured data extraction, and relation extraction with CPU-optimized inference.
@@ -297,12 +555,31 @@ The T5-Gemma model excels at:
 
 GLiNER2 now handles:
 - **Entity recognition** - refining subject/object boundaries
-- **Relation extraction** - when predefined predicates are provided
+- **Relation extraction** - using 324 default predicates across 21 categories
 - **Entity scoring** - scoring how "entity-like" subjects/objects are
+- **Confidence scoring** - real confidence values via `include_confidence=True`
+
+### Default Predicates
+
+GLiNER2 uses **324 predicates** organized into 21 categories (ownership, employment, funding, etc.). These are loaded from `default_predicates.json` and include descriptions and confidence thresholds.
 
-### Two Extraction Modes
+**Key features:**
+- **All matches returned** - Every matching relation is returned, not just the best one
+- **Category-based extraction** - Iterates through categories to stay under GLiNER2's ~25 label limit
+- **Custom predicate files** - Provide your own JSON file with custom predicates
 
-**Mode 1: With Predicate List** (GLiNER2 relation extraction)
+### Extraction Modes
+
+**Mode 1: Default Predicates** (recommended)
+```python
+from statement_extractor import extract_statements
+
+# Uses 324 built-in predicates automatically
+result = extract_statements("John works for Apple Inc. in Cupertino.")
+# Returns ALL matching relations
+```
+
+**Mode 2: Custom Predicate List**
 ```python
 from statement_extractor import extract_statements, ExtractionOptions
 
@@ -315,27 +592,35 @@ Or via CLI:
 corp-extractor "John works for Apple Inc." --predicates "works_for,founded,acquired"
 ```
 
-**Mode 2: Without Predicate List** (entity-refined extraction)
+**Mode 3: Custom Predicate File**
 ```python
-result = extract_statements("Apple announced a new iPhone.")
-# Uses GLiNER2 for entity extraction to refine boundaries
-# Extracts predicate from source text using T5-Gemma's hint
+from statement_extractor.pipeline import ExtractionPipeline, PipelineConfig
+
+config = PipelineConfig(
+    extractor_options={"predicates_file": "/path/to/custom_predicates.json"}
+)
+pipeline = ExtractionPipeline(config)
+ctx = pipeline.process("John works for Apple Inc.")
+```
+
+Or via CLI:
+```bash
+corp-extractor pipeline "John works for Apple Inc." --predicates-file custom_predicates.json
 ```
 
-### Three Candidate Extraction Methods
+### Two Candidate Extraction Methods
 
-For each statement, three candidates are generated and the best is selected:
+For each statement, two candidates are generated and the best is selected:
 
 | Method | Description |
 |--------|-------------|
 | `hybrid` | Model subject/object + GLiNER2/extracted predicate |
-| `gliner` | All components refined by GLiNER2 |
-| `split` | Source text split around the predicate |
+| `gliner` | All components refined by GLiNER2 entity recognition |
 
 ```python
 for stmt in result:
     print(f"{stmt.subject.text} --[{stmt.predicate}]--> {stmt.object.text}")
-    print(f"  Method: {stmt.extraction_method}")  # hybrid, gliner, split, or model
+    print(f"  Method: {stmt.extraction_method}")  # hybrid, gliner, or model
     print(f"  Confidence: {stmt.confidence_score:.2f}")
 ```
 
@@ -359,8 +644,7 @@ Confidence scores combine **semantic similarity** and **entity recognition**:
 
 Each statement includes an `extraction_method` field:
 - `hybrid` - Model subject/object + GLiNER2 predicate
-- `gliner` - All components refined by GLiNER2
-- `split` - Subject/object from splitting source text around predicate
+- `gliner` - All components refined by GLiNER2 entity recognition
 - `model` - All components from T5-Gemma model (only when `--no-gliner`)
 
 ### Best Triple Selection

corp_extractor-0.9.0.dist-info/RECORD

@@ -0,0 +1,76 @@
+statement_extractor/__init__.py,sha256=vOJFsK6wNOoBvGYOvIKsseaqpFR8vNg_XPH-r8SmLas,3215
+statement_extractor/canonicalization.py,sha256=ZMLs6RLWJa_rOJ8XZ7PoHFU13-zeJkOMDnvK-ZaFa5s,5991
+statement_extractor/cli.py,sha256=BTFLIBZoNa2ADrYVslbXiZGrzhRWmi7ppbnAPV3xUyg,71191
+statement_extractor/extractor.py,sha256=CGJCmAMiIoDsPtjIdvOHYBcz8058eYpfLMngjELMJhI,38403
+statement_extractor/gliner_extraction.py,sha256=OL4w-0_rZc6XCojaVsbGY4VdIXRJ6j8ZmeUeTOL0Ue0,8118
+statement_extractor/llm.py,sha256=1eBrYs-bUPqzbpiiif_hH-gE_DeM-l3cmddrIoLHFXo,8010
+statement_extractor/models.py,sha256=fXTT7qxPqynnrrpb77nCgs3K2yn_YgbSugSXv12boX4,12312
+statement_extractor/predicate_comparer.py,sha256=jcuaBi5BYqD3TKoyj3pR9dxtX5ihfDJvjdhEd2LHCwc,26184
+statement_extractor/scoring.py,sha256=V9WHQ-QCAoycnnaTHydWkFo-48_lcS6Mkztxjfi4wVg,16632
+statement_extractor/data/default_predicates.json,sha256=7rhFXWHvStDj4sLYfBXKS50xGChPaqMKUaKTkMEJRGk,32870
+statement_extractor/data/statement_taxonomy.json,sha256=LI9RWthuJTFCcuaIbh6h3FEu8EJpejiKjAtNM_y1s8A,336543
+statement_extractor/database/__init__.py,sha256=1eScQOm7866v9xndaqCK-xsXDUhKBSj5YGtGoQ80LgU,1548
+statement_extractor/database/embeddings.py,sha256=j_gUTEdRyyQCPcx9imsOh1nVDPjeiRXXG22OZ7KIO4w,5535
+statement_extractor/database/hub.py,sha256=HOnRp62RnkXvk2KgwqOLVpEkXwy0LS0n3tIJrkYCo2c,16842
+statement_extractor/database/models.py,sha256=ke4byqJiiBlZfRhxqoC0nsdDhb6YSG2I4S5W5BRBNY4,8813
+statement_extractor/database/resolver.py,sha256=_fTITarFmAYOtuRbOos48ou_aqX4yJC0K2csdLbIktI,7202
+statement_extractor/database/store.py,sha256=1qdRZ7q5nTLUYbtUC9cWSLey_GVf5kAQ6dTF9EEwDXY,56735
+statement_extractor/database/importers/__init__.py,sha256=0CPqafekQpqxFmZhe3uMJLNssqxGzEniZlArGyl8QKU,668
+statement_extractor/database/importers/companies_house.py,sha256=G0DZAs_9RM7uTwY7imt70IXUVvhntoO-xXnJ0o6jjGw,19635
+statement_extractor/database/importers/gleif.py,sha256=MTFuksVf83Barn1c6JvBLBouxXbzogWulKb8oqEODAk,18948
+statement_extractor/database/importers/sec_edgar.py,sha256=_B4QcXhZ_5ulXTSVW9dKKAzFIVwn-VIh_X39jcUhqsg,12923
+statement_extractor/database/importers/wikidata.py,sha256=ZZYHiqSlYlco1TSzCLUKqdT-i5X1cUSK1EnsfWWwPAc,33770
+statement_extractor/database/importers/wikidata_people.py,sha256=loqyf5sbtBqCITiTxqV3PLyx3SefmVefhZE0Y-cRoC4,22205
+statement_extractor/document/__init__.py,sha256=csbUUjxaZay-0WXtjZmULjDfL9VNxhOlePyKTMdRDYo,1714
+statement_extractor/document/chunker.py,sha256=I76p6Qwujk2kkN7GJ1sMwbQNOfEpbt29u-RxJdt15oE,14020
+statement_extractor/document/context.py,sha256=9DvyguwCjlef2MeNWZMgydvD54FPiOppjdvamQnrKzM,5450
+statement_extractor/document/deduplicator.py,sha256=8tPKWAGqNfjteOdnk7B82izyfIpvOebirZ-OIQKixwU,4821
+statement_extractor/document/html_extractor.py,sha256=YRhaIsurBJTeECLkL2YJsSv8gDJJN33fS-ESkGvDBGs,6600
+statement_extractor/document/loader.py,sha256=Ygund7bz4EVcwsFsxkrrgSjOCK4tbb_sqkMlzK_oEKM,8996
+statement_extractor/document/pipeline.py,sha256=h4q-CG_WtBLibkTXCFhfTizMme8bJS5f6ZWOECqhRYU,13675
+statement_extractor/document/summarizer.py,sha256=DOF6qPw0oWEtLSt97oXOFyzb0jGWZZ7frDFp11rL3is,5853
+statement_extractor/models/__init__.py,sha256=9FxKkJ4EIPXmSkMo_j9jqAKH6jTkvz5Tzk2YvQL7UVk,2884
+statement_extractor/models/canonical.py,sha256=LaSU3CUJZOtBM1SpRTAmK-3N7QnYmxZYJvQE1NVIjLY,6003
+statement_extractor/models/document.py,sha256=McCyXz88YtJtlsfiFzagjRAhY32ovpIDKXQI_eV_DZI,9203
+statement_extractor/models/entity.py,sha256=l2ny91BnnWwPo9zx1_Fb8WMKPNuIQFN0H7ILncylmcY,3214
+statement_extractor/models/labels.py,sha256=NUcjFDuGUOM82mgsaWOdoIVbRNiQ6TdN-imNuTograo,7326
+statement_extractor/models/qualifiers.py,sha256=l--khVzt-N6jgibZ-MSSl-3SdQUZJN9dGoxdNhRmM_I,5926
+statement_extractor/models/statement.py,sha256=agC4jcP9ospbZC91J6c0UgLAmfsg1tnqNcSvkqOtqBQ,3629
+statement_extractor/pipeline/__init__.py,sha256=Q3M2Arx9BWH_APZxM-P0G-C3ISguG1whiA5QhxDHQCA,1071
+statement_extractor/pipeline/config.py,sha256=FXtqMMpRmdeuHB86D6YrFx5A36XHVg5GlBBZuPEn4JA,3957
+statement_extractor/pipeline/context.py,sha256=wURDYtzDrmbHu40Af_C_oTtN55wnULKHNZjUx6O8t-0,6126
+statement_extractor/pipeline/orchestrator.py,sha256=1pe6hyEtd495LJrfH3QgxQadNqERmehQEs5LHsAVIxM,16580
+statement_extractor/pipeline/registry.py,sha256=yBybhRd1HU2Y75TebLGBzF6nbPiHKZ0cHkyj-3CVnhg,11390
+statement_extractor/plugins/__init__.py,sha256=pIcPeoMFd-56jOM_kGrUWvPuwqN6vFJ-oUbu130-tzI,1345
+statement_extractor/plugins/base.py,sha256=ItqJZ5rH65gW4-pXpraRb45y7F3lXqsKECumhV3tDyk,21516
+statement_extractor/plugins/extractors/__init__.py,sha256=sqxTI7WwDLVQKwOiQXqWS72gjJnwb76Gs9N3LGetBnI,253
+statement_extractor/plugins/extractors/base.py,sha256=kNRsQ7BL84lXPXREm7CihrprDUaFwDDvMpBcbZlwSGA,179
+statement_extractor/plugins/extractors/gliner2.py,sha256=ObEQMNE6ArjRl2s4x3lkOSPs03cmtTYFlppnbhtkI7A,21876
+statement_extractor/plugins/labelers/__init__.py,sha256=flHEoBvnzQ3vAKkIUHyezpYi2H3KJvYGRerCVnc80r0,965
+statement_extractor/plugins/labelers/base.py,sha256=hIgJKq2LU00OcL0Zjy1L9hP8K2onlM_xtZ63XcH8qDE,171
+statement_extractor/plugins/labelers/confidence.py,sha256=XiXjBYe-8ch_SCKnz0sAwTT1mJ_XKMsuzXBbwAW_OK0,4083
+statement_extractor/plugins/labelers/relation_type.py,sha256=e5ASwVqJGMSCrx5GtyNk85q_-19D7W_4jI-J-Pv_kxY,2506
+statement_extractor/plugins/labelers/sentiment.py,sha256=nlWv9ymb7hlDIcFa-gjbIvZlJY1VrHrXhKMD-udmIzM,5027
+statement_extractor/plugins/labelers/taxonomy.py,sha256=u_TQVCTOZCtZis5ZP0xvxh5Ehc0fCJ-DG6E86GxjNcs,12725
+statement_extractor/plugins/labelers/taxonomy_embedding.py,sha256=NsSls2jkWm8LyNNuDkG2Rs4PYKQQxeMUDLTRrvSNk_A,16305
+statement_extractor/plugins/pdf/__init__.py,sha256=QLbgg3lgpwUKR1EGmzhbOJh5IB4-3rpWen9c75YNLtM,220
+statement_extractor/plugins/pdf/pypdf.py,sha256=JgmWa1-6tiATbPvhONMqRd5kAXJ--tb8rlEcR3u73sk,8612
+statement_extractor/plugins/qualifiers/__init__.py,sha256=H4FEZSw1GWBQB-Y79nQnLwhZ3okKQJqgJHGEA0Zp8pA,951
+statement_extractor/plugins/qualifiers/base.py,sha256=Kx--OdIh77mnjSkTl1NvUeekItRiG8AnBUcuznOZeBI,179
+statement_extractor/plugins/qualifiers/companies_house.py,sha256=6TlK6Zebb5wDJ9GGO3FvM9zOh27TWpio5BX9k7lBr7U,5854
+statement_extractor/plugins/qualifiers/embedding_company.py,sha256=EmCxImdXBCA7zxM1stAVeAYlzeNPC_jSlyVN5q1XEJA,14567
+statement_extractor/plugins/qualifiers/gleif.py,sha256=zHzC9eOt0R9Z56n0CXgTF7POJqu6v03SRmiJLmv8OGE,6104
+statement_extractor/plugins/qualifiers/person.py,sha256=GZCUJaQncC_wB4nBQ4RLY5dJ-CdARMLpByc_Nn09wj8,28461
+statement_extractor/plugins/qualifiers/sec_edgar.py,sha256=d7QqGiE-3lFDQiXkYmNQU62K4oP2XYK6NzV6LNKPC5k,6754
+statement_extractor/plugins/scrapers/__init__.py,sha256=mh1nmPtcsewrYeW5oELeke6DSzL8jsGOJ2OcH-A4-eo,208
+statement_extractor/plugins/scrapers/http.py,sha256=igoB1JN7U-FPdBFmNfrdZV-Ho4JQ3RXniLz17SmQx8I,7778
+statement_extractor/plugins/splitters/__init__.py,sha256=05CYeAEO0lZsapK5pjxZJbOCLI1kjeK6IQjftxqqg5g,224
+statement_extractor/plugins/splitters/base.py,sha256=GeIBchFTr8icRSfYR8bGSb4-GoEZ1N0IGN6Kl5W2mL0,175
+statement_extractor/plugins/splitters/t5_gemma.py,sha256=AwYYKQrAmiue5IK9bbJ-Uhfl9oCZTX1X_tmKguKIdjU,9982
+statement_extractor/plugins/taxonomy/__init__.py,sha256=8N0tW7pm95DSCqM-s99ea0Tigbi9bZMyTkKblR1qmLw,307
+statement_extractor/plugins/taxonomy/embedding.py,sha256=yCuNE8UeY8tH2dHGRKL3hmRQBmdz9_9YQ0t5_VTCf7E,16349
+statement_extractor/plugins/taxonomy/mnli.py,sha256=zPZlpAHQqdnwH7fXS_CSY0HCMnaSrrk-fDQb1ZIqqPc,9163
+corp_extractor-0.9.0.dist-info/METADATA,sha256=9pWemKEWyeEqW92sRd4SqdMykO-92kl5UIrs-P2xAn0,27553
+corp_extractor-0.9.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+corp_extractor-0.9.0.dist-info/entry_points.txt,sha256=i0iKFqPIusvb-QTQ1zNnFgAqatgVah-jIhahbs5TToQ,115
+corp_extractor-0.9.0.dist-info/RECORD,,

statement_extractor/__init__.py

@@ -29,7 +29,7 @@ Example:
     >>> data = extract_statements_as_dict("Some text...")
 """
 
-__version__ = "0.3.0"
+__version__ = "0.6.0"
 
 # Core models
 from .models import (
@@ -97,6 +97,9 @@ __all__ = [
     # Scoring
     "BeamScorer",
     "TripleScorer",
+    # LLM (lazy import)
+    "LLM",
+    "get_llm",
 ]
 
 
@@ -109,4 +112,10 @@ def __getattr__(name: str):
     if name == "EmbeddingDependencyError":
         from .predicate_comparer import EmbeddingDependencyError
         return EmbeddingDependencyError
+    if name == "LLM":
+        from .llm import LLM
+        return LLM
+    if name == "get_llm":
+        from .llm import get_llm
+        return get_llm
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")