corp-extractor 0.3.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

{corp_extractor-0.3.0.dist-info → corp_extractor-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: corp-extractor
-Version: 0.3.0
+Version: 0.5.0
 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
@@ -23,11 +23,13 @@ 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: click>=8.0.0
+Requires-Dist: gguf>=0.17.1
+Requires-Dist: gliner2
 Requires-Dist: numpy>=1.24.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: sentence-transformers>=2.2.0
-Requires-Dist: spacy>=3.5.0
 Requires-Dist: torch>=2.0.0
 Requires-Dist: transformers>=5.0.0rc3
 Provides-Extra: dev
@@ -35,6 +37,8 @@ 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'
 Description-Content-Type: text/markdown
 
 # Corp Extractor
@@ -47,20 +51,18 @@ Extract structured subject-predicate-object statements from unstructured text us
 
 ## Features
 
+- **6-Stage Pipeline** *(v0.5.0)*: Modular plugin-based architecture for full entity resolution
 - **Structured Extraction**: Converts unstructured text into subject-predicate-object triples
 - **Entity Type Recognition**: Identifies 12 entity types (ORG, PERSON, GPE, LOC, PRODUCT, EVENT, etc.)
-- **Combined Quality Scoring** *(v0.3.0)*: Confidence combines semantic similarity (50%) + subject/object noun scores (25% each)
-- **spaCy-First Predicates** *(v0.3.0)*: Always uses spaCy for predicate extraction (model predicates are unreliable)
-- **Multi-Candidate Extraction** *(v0.3.0)*: Generates 3 candidates per statement (hybrid, spaCy-only, predicate-split)
-- **Best Triple Selection** *(v0.3.0)*: Keeps only highest-scoring triple per source (use `--all-triples` to keep all)
-- **Extraction Method Tracking** *(v0.3.0)*: Each statement includes `extraction_method` field (hybrid, spacy, split, model)
-- **Beam Merging** *(v0.2.0)*: Combines top beams for better coverage instead of picking one
-- **Embedding-based Dedup** *(v0.2.0)*: Uses semantic similarity to detect near-duplicate predicates
-- **Predicate Taxonomies** *(v0.2.0)*: Normalize predicates to canonical forms via embeddings
-- **Contextualized Matching** *(v0.2.2)*: Compares full "Subject Predicate Object" against source text for better accuracy
-- **Entity Type Merging** *(v0.2.3)*: Automatically merges UNKNOWN entity types with specific types during deduplication
-- **Reversal Detection** *(v0.2.3)*: Detects and corrects subject-object reversals using embedding comparison
-- **Command Line Interface** *(v0.2.4)*: Full-featured CLI for terminal usage
+- **Entity Qualification** *(v0.5.0)*: Adds roles, identifiers (LEI, ticker, company numbers) via external APIs
+- **Canonicalization** *(v0.5.0)*: Resolves entities to canonical forms with fuzzy matching
+- **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**: 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
+- **Command Line Interface**: Full-featured CLI with `split`, `pipeline`, and `plugins` commands
 - **Multiple Output Formats**: Get results as Pydantic models, JSON, XML, or dictionaries
 
 ## Installation
@@ -69,7 +71,7 @@ Extract structured subject-predicate-object statements from unstructured text us
 pip install corp-extractor
 ```
 
-The spaCy model for predicate inference is downloaded automatically on first use.
+The GLiNER2 model (205M params) is downloaded automatically on first use.
 
 **Note**: This package requires `transformers>=5.0.0` for T5-Gemma2 model support.
 
@@ -134,62 +136,74 @@ 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 6-stage pipeline (entity resolution, canonicalization, 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]
+
+Commands:
+  split      Simple extraction (T5-Gemma only)
+  pipeline   Full 5-stage pipeline with entity resolution
+  plugins    List or inspect available plugins
 
-Options:
+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-spacy                   Disable spaCy extraction (use raw model output)
-  --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
@@ -283,69 +297,194 @@ 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.
 
-## New in v0.3.0: spaCy-First Extraction & Semantic Scoring
+## New in v0.5.0: Pipeline Architecture
+
+v0.5.0 introduces a **6-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 | `QualifiedEntity[]` | Gemma3, APIs |
+| 4 | Canonicalization | `QualifiedEntity[]` | `CanonicalEntity[]` | Fuzzy matching |
+| 5 | Labeling | Statements | `LabeledStatement[]` | Sentiment, etc. |
+| 6 | 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 canonicalization and labeling
+    disabled_plugins={"sec_edgar_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 (uses Gemma3)
+- `gleif_qualifier` - ORG → LEI, jurisdiction (GLEIF API)
+- `companies_house_qualifier` - ORG → UK company number
+- `sec_edgar_qualifier` - ORG → SEC CIK, ticker
+
+**Canonicalizers (Stage 4):**
+- `organization_canonicalizer` - ORG canonical names
+- `person_canonicalizer` - PERSON name variants
 
-v0.3.0 introduces significant improvements to extraction quality:
+**Labelers (Stage 5):**
+- `sentiment_labeler` - Statement sentiment analysis
 
-### spaCy-First Predicate Extraction
+**Taxonomy Classifiers (Stage 6):**
+- `mnli_taxonomy_classifier` - MNLI zero-shot classification against ESG taxonomy
+- `embedding_taxonomy_classifier` - Embedding similarity-based taxonomy classification
 
-The T5-Gemma model is excellent at:
+Taxonomy classifiers return **multiple labels** per statement above the confidence threshold.
+
+## 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.
+
+### Why GLiNER2?
+
+The T5-Gemma model excels at:
 - **Triple isolation** - identifying that a relationship exists
 - **Coreference resolution** - resolving pronouns to named entities
 
-But unreliable at:
-- **Predicate extraction** - often returns empty or wrong predicates
+GLiNER2 now handles:
+- **Entity recognition** - refining subject/object boundaries
+- **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.
+
+**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
+
+### 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
+
+options = ExtractionOptions(predicates=["works_for", "founded", "acquired", "headquartered_in"])
+result = extract_statements("John works for Apple Inc. in Cupertino.", options)
+```
 
-**Solution:** v0.3.0 always uses spaCy for predicate extraction. The model provides subject, object, entity types, and source text; spaCy provides the predicate.
+Or via CLI:
+```bash
+corp-extractor "John works for Apple Inc." --predicates "works_for,founded,acquired"
+```
 
-### Three Candidate Extraction Methods
+**Mode 3: Custom Predicate File**
+```python
+from statement_extractor.pipeline import ExtractionPipeline, PipelineConfig
 
-For each statement, three candidates are generated and the best is selected:
+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
+```
+
+### Two Candidate Extraction Methods
+
+For each statement, two candidates are generated and the best is selected:
 
 | Method | Description |
 |--------|-------------|
-| `hybrid` | Model subject/object + spaCy predicate |
-| `spacy` | All components from spaCy dependency parsing |
-| `split` | Source text split around the predicate |
+| `hybrid` | Model subject/object + GLiNER2/extracted 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, spacy, split, or model
+    print(f"  Method: {stmt.extraction_method}")  # hybrid, gliner, or model
     print(f"  Confidence: {stmt.confidence_score:.2f}")
 ```
 
 ### Combined Quality Scoring
 
-Confidence scores combine **semantic similarity** and **grammatical accuracy**:
+Confidence scores combine **semantic similarity** and **entity recognition**:
 
 | Component | Weight | Description |
 |-----------|--------|-------------|
 | Semantic similarity | 50% | Cosine similarity between source text and reassembled triple |
-| Subject noun score | 25% | How noun-like the subject is |
-| Object noun score | 25% | How noun-like the object is |
-
-**Noun scoring:**
-- Proper noun(s) only: 1.0
-- Common noun(s) only: 0.8
-- Contains noun + other words: 0.4-0.8 (based on ratio)
-- No nouns: 0.2
+| Subject entity score | 25% | How entity-like the subject is (via GLiNER2) |
+| Object entity score | 25% | How entity-like the object is (via GLiNER2) |
 
-This ensures extracted subjects and objects are grammatically valid entities, not fragments or verb phrases.
+**Entity scoring (via GLiNER2):**
+- Recognized entity with high confidence: 1.0
+- Recognized entity with moderate confidence: 0.8
+- Partially recognized: 0.6
+- Not recognized: 0.2
 
 ### Extraction Method Tracking
 
-Each statement now includes an `extraction_method` field:
-- `hybrid` - Model subject/object + spaCy predicate
-- `spacy` - All components from spaCy dependency parsing
-- `split` - Subject/object from splitting source text around predicate
-- `model` - All components from T5-Gemma model (only when `--no-spacy`)
+Each statement includes an `extraction_method` field:
+- `hybrid` - Model subject/object + GLiNER2 predicate
+- `gliner` - All components refined by GLiNER2 entity recognition
+- `model` - All components from T5-Gemma model (only when `--no-gliner`)
 
 ### Best Triple Selection
 
-By default, only the **highest-scoring triple** is kept for each source sentence. This ensures clean output without redundant candidates.
+By default, only the **highest-scoring triple** is kept for each source sentence.
 
-To keep all candidate triples (for debugging or analysis):
+To keep all candidate triples:
 ```python
 options = ExtractionOptions(all_triples=True)
 result = extract_statements(text, options)
@@ -356,15 +495,15 @@ Or via CLI:
 corp-extractor "Your text" --all-triples --verbose
 ```
 
-**Disable spaCy extraction** to use only model output:
+**Disable GLiNER2 extraction** to use only model output:
 ```python
-options = ExtractionOptions(use_spacy_extraction=False)
+options = ExtractionOptions(use_gliner_extraction=False)
 result = extract_statements(text, options)
 ```
 
 Or via CLI:
 ```bash
-corp-extractor "Your text" --no-spacy
+corp-extractor "Your text" --no-gliner
 ```
 
 ## Disable Embeddings
@@ -436,14 +575,14 @@ for text in texts:
 This library uses the T5-Gemma 2 statement extraction model with **Diverse Beam Search** ([Vijayakumar et al., 2016](https://arxiv.org/abs/1610.02424)):
 
 1. **Diverse Beam Search**: Generates 4+ candidate outputs using beam groups with diversity penalty
-2. **Quality Scoring** *(v0.2.0)*: Each triple scored for groundedness in source text
-3. **Beam Merging** *(v0.2.0)*: Top beams combined for better coverage
-4. **Embedding Dedup** *(v0.2.0)*: Semantic similarity removes near-duplicate predicates
-5. **Predicate Normalization** *(v0.2.0)*: Optional taxonomy matching via embeddings
-6. **Contextualized Matching** *(v0.2.2)*: Full statement context used for canonicalization and dedup
-7. **Entity Type Merging** *(v0.2.3)*: UNKNOWN types merged with specific types during dedup
-8. **Reversal Detection** *(v0.2.3)*: Subject-object reversals detected and corrected via embedding comparison
-9. **Hybrid spaCy** *(v0.2.12)*: spaCy candidates added to pool alongside model output for better coverage
+2. **Quality Scoring**: Each triple scored for groundedness in source text
+3. **Beam Merging**: Top beams combined for better coverage
+4. **Embedding Dedup**: Semantic similarity removes near-duplicate predicates
+5. **Predicate Normalization**: Optional taxonomy matching via embeddings
+6. **Contextualized Matching**: Full statement context used for canonicalization and dedup
+7. **Entity Type Merging**: UNKNOWN types merged with specific types during dedup
+8. **Reversal Detection**: Subject-object reversals detected and corrected via embedding comparison
+9. **GLiNER2 Extraction** *(v0.4.0)*: Entity recognition and relation extraction for improved accuracy
 
 ## Requirements
 
@@ -452,7 +591,7 @@ This library uses the T5-Gemma 2 statement extraction model with **Diverse Beam
 - Transformers 5.0+
 - Pydantic 2.0+
 - sentence-transformers 2.2+
-- spaCy 3.5+ (model downloaded automatically on first use)
+- GLiNER2 (model downloaded automatically on first use)
 - ~2GB VRAM (GPU) or ~4GB RAM (CPU)
 
 ## Links

corp_extractor-0.5.0.dist-info/RECORD

@@ -0,0 +1,55 @@
+statement_extractor/__init__.py,sha256=Lmgw3jtwrfu09mXSfNFCB5AN0J6tsEQ2uOrrQciMrtI,3215
+statement_extractor/canonicalization.py,sha256=ZMLs6RLWJa_rOJ8XZ7PoHFU13-zeJkOMDnvK-ZaFa5s,5991
+statement_extractor/cli.py,sha256=iqsqvLAN0FMRoE4KskEoW-4DE5_7Tll8xeHA1t04KJg,25028
+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=s_8nhavBNzPPFmGf2FyBummH4tgP7YGpXoMhl2Jh3Xw,16650
+statement_extractor/data/default_predicates.json,sha256=7rhFXWHvStDj4sLYfBXKS50xGChPaqMKUaKTkMEJRGk,32870
+statement_extractor/data/statement_taxonomy.json,sha256=XhCeVBC4aQB-7NR40Niu4yN2BmL0c2Gd-RKkUpsYK24,37981
+statement_extractor/models/__init__.py,sha256=gjTu450FPe9dvhIVQXqBwF8u0hgSnPORGXzxmSEuCnM,2564
+statement_extractor/models/canonical.py,sha256=ld6z6RtK03iOs_aUk8Rftcm0pUoaFpLUfyfbKI26N_o,4354
+statement_extractor/models/entity.py,sha256=l2ny91BnnWwPo9zx1_Fb8WMKPNuIQFN0H7ILncylmcY,3214
+statement_extractor/models/labels.py,sha256=e-mFDuzb42oJ69gLZTWCdg5_MNqRftQ2La5x8y9Cv-Y,6236
+statement_extractor/models/qualifiers.py,sha256=YkvyWh2p1fK5iMRDC2Dq1r-XJOmJ1rvWFTFUIkQ9zcc,3495
+statement_extractor/models/statement.py,sha256=cOgabA7IJxHYjlH5AksJRNf2Rv5VScMPqZdfjQyXRN0,2733
+statement_extractor/pipeline/__init__.py,sha256=Q3M2Arx9BWH_APZxM-P0G-C3ISguG1whiA5QhxDHQCA,1071
+statement_extractor/pipeline/config.py,sha256=rxZN27OWp05F-NaatwrYkjp56zbzHZ0hMtNU1mvBxgw,4130
+statement_extractor/pipeline/context.py,sha256=wURDYtzDrmbHu40Af_C_oTtN55wnULKHNZjUx6O8t-0,6126
+statement_extractor/pipeline/orchestrator.py,sha256=oHegnsDzXj87q8iAoi-QZj2ZyB1rX5qmg57BdIjvKo0,17617
+statement_extractor/pipeline/registry.py,sha256=qj5M5tMm9GmNCguy8dWBXMT8XmhemiZjJMktZsRlevw,11415
+statement_extractor/plugins/__init__.py,sha256=8k3lQGQNQSMUzxCmk4nAH8dIc1DqEnMyiqHlZZv81q0,1099
+statement_extractor/plugins/base.py,sha256=GZ4WT5S2mH3C_uN6nyBz-nGlAn_Z2o2A51FSRu6gCEo,12797
+statement_extractor/plugins/canonicalizers/__init__.py,sha256=LDb9NodyuLSoLzrLnNzMeviK79GHnyaLGU0J_02BBgM,421
+statement_extractor/plugins/canonicalizers/base.py,sha256=dbreQuEPB48eBJmah7hpl67azVU4QLhbvSrjXr0vT88,195
+statement_extractor/plugins/canonicalizers/location.py,sha256=Rz5SCM4bb0p0gsnHPzsQJv-RN59yoj9Z1NmF8yLQNv0,6590
+statement_extractor/plugins/canonicalizers/organization.py,sha256=L-mhdctkRXuu84RsNHp80M_tDIiMumYaHAG6WfxpH4c,7482
+statement_extractor/plugins/canonicalizers/person.py,sha256=Nw8FuJOBmg-cTaOTd2BJ1TZtydprfzIKL25wJa_VJek,6944
+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=rgfY8l9v8EWCxfB3g6hLnmLCIekTBkfWMG8dgSAZu-E,21627
+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=jQp5emgWf6XgmOx7arh-owF_-TjVxiPKSJ2OGkTPbBs,12427
+statement_extractor/plugins/labelers/taxonomy_embedding.py,sha256=grvC_R_sg05hR6l0DgaELy2wmf6OkbvV1pRuNU0FVk4,16027
+statement_extractor/plugins/qualifiers/__init__.py,sha256=kefjGunlVDKLy2NXmtr5ZXyYi-swyQdPLkB-tHV_0vk,495
+statement_extractor/plugins/qualifiers/base.py,sha256=Kx--OdIh77mnjSkTl1NvUeekItRiG8AnBUcuznOZeBI,179
+statement_extractor/plugins/qualifiers/companies_house.py,sha256=_6ExJCjD0V4eZNYXtfBY99obqLpRaSv-G-V7N6R1wLg,5376
+statement_extractor/plugins/qualifiers/gleif.py,sha256=WZqcNT_Yq4yVe4rdkWO59C9yZ4geV2ZTDk9wxLlOeTg,5645
+statement_extractor/plugins/qualifiers/person.py,sha256=si_9CLjHsH9jYFugej4t0HMnsivclh-Yi70U6NglfIU,7101
+statement_extractor/plugins/qualifiers/sec_edgar.py,sha256=3XDbizlR9YQgLrC7p-owV8Td-3TYaJlMb4B7saha3vw,6288
+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=8joOzlMKXhSyJaq5c3F8t-gdPcZEDiVAzNcMlgJAqsE,6733
+statement_extractor/plugins/taxonomy/__init__.py,sha256=8N0tW7pm95DSCqM-s99ea0Tigbi9bZMyTkKblR1qmLw,307
+statement_extractor/plugins/taxonomy/embedding.py,sha256=QW1RR07JoE8Ah97gDZ_w_ATEe6-z2t2nl1zeTDAgFjM,11347
+statement_extractor/plugins/taxonomy/mnli.py,sha256=IzLjHXUFgVAgEvYI5EzOBs19UxvpcbJa8HjqI__tYII,8905
+corp_extractor-0.5.0.dist-info/METADATA,sha256=H4Z8ExZFdbknpHg-EZ1P9B137hCPwKXBezHSF7X9EOE,21567
+corp_extractor-0.5.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+corp_extractor-0.5.0.dist-info/entry_points.txt,sha256=i0iKFqPIusvb-QTQ1zNnFgAqatgVah-jIhahbs5TToQ,115
+corp_extractor-0.5.0.dist-info/RECORD,,

statement_extractor/__init__.py

@@ -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}")