corp-extractor 0.5.0__py3-none-any.whl → 0.9.3__py3-none-any.whl

{corp_extractor-0.5.0.dist-info → corp_extractor-0.9.3.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: corp-extractor
-Version: 0.5.0
-Summary: Extract structured statements from text using T5-Gemma 2 and Diverse Beam Search
+Version: 0.9.3
+Summary: Extract structured entity and relationship information from text
 Project-URL: Homepage, https://github.com/corp-o-rate/statement-extractor
 Project-URL: Documentation, https://github.com/corp-o-rate/statement-extractor#readme
 Project-URL: Repository, https://github.com/corp-o-rate/statement-extractor
@@ -9,7 +9,7 @@ Project-URL: Issues, https://github.com/corp-o-rate/statement-extractor/issues
 Author-email: Corp-o-Rate <neil@corp-o-rate.com>
 Maintainer-email: Corp-o-Rate <neil@corp-o-rate.com>
 License: MIT
-Keywords: diverse-beam-search,embeddings,gemma,information-extraction,knowledge-graph,nlp,statement-extraction,subject-predicate-object,t5,transformers,triples
+Keywords: diverse-beam-search,embeddings,entities,entity-linking,entity-resolution,gemma,information-extraction,knowledge-graph,nlp,semantic-parsing,statement-extraction,subject-predicate-object,t5gemma2,transformers,triples
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -24,14 +24,25 @@ 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: pycountry>=24.6.1
 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'
@@ -39,6 +50,9 @@ 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
@@ -51,18 +65,21 @@ 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
+- **Person Database** *(v0.9.2)*: Qualify notable people (executives, politicians, athletes, etc.) against Wikidata with canonical IDs
+- **Organization Canonicalization** *(v0.9.2)*: Link equivalent records across sources (LEI, ticker, CIK, name matching)
+- **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** *(v0.5.0)*: Adds roles, identifiers (LEI, ticker, company numbers) via external APIs
-- **Canonicalization** *(v0.5.0)*: Resolves entities to canonical forms with fuzzy matching
+- **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**: 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
+- **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
@@ -143,7 +160,7 @@ The CLI provides three main commands: `split`, `pipeline`, and `plugins`.
 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)
+# 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
@@ -206,10 +223,10 @@ Pipeline Options:
   -o, --output [table|json|yaml|triples]  Output format
 ```
 
-## New in v0.2.0: Quality Scoring & Beam Merging
+## Quality Scoring & Beam Merging
 
-By default, the library now:
-- **Scores each triple** for groundedness based on whether entities appear in source text
+By default, the library:
+- **Scores each triple** using semantic similarity (50%) + GLiNER2 entity recognition (50%)
 - **Merges top beams** instead of selecting one, improving coverage
 - **Uses embeddings** to detect semantically similar predicates ("bought" ≈ "acquired")
 
@@ -297,9 +314,9 @@ 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 v0.5.0: Pipeline Architecture
+## Pipeline Architecture
 
-v0.5.0 introduces a **6-stage plugin-based pipeline** for comprehensive entity resolution, statement enrichment, and taxonomy classification.
+The library uses a **5-stage plugin-based pipeline** for comprehensive entity resolution, statement enrichment, and taxonomy classification.
 
 ### Pipeline Stages
 
@@ -307,10 +324,9 @@ v0.5.0 introduces a **6-stage plugin-based pipeline** for comprehensive entity r
 |-------|------|-------|--------|----------|
 | 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 |
+| 3 | Qualification | Entities | `CanonicalEntity[]` | Embedding DB |
+| 4 | Labeling | Statements | `LabeledStatement[]` | Sentiment, etc. |
+| 5 | Taxonomy | Statements | `TaxonomyResult[]` | MNLI, Embeddings |
 
 ### Pipeline Python API
 
@@ -339,8 +355,8 @@ 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
+    enabled_stages={1, 2, 3},  # Skip labeling and taxonomy
+    disabled_plugins={"person_qualifier"},  # Disable specific plugins
 )
 pipeline = ExtractionPipeline(config)
 ctx = pipeline.process(text)
@@ -358,24 +374,206 @@ config = PipelineConfig.from_stage_string("1-3")  # Stages 1, 2, 3
 - `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
+- `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
 
-**Canonicalizers (Stage 4):**
-- `organization_canonicalizer` - ORG canonical names
-- `person_canonicalizer` - PERSON name variants
-
-**Labelers (Stage 5):**
+**Labelers (Stage 4):**
 - `sentiment_labeler` - Statement sentiment analysis
+- `confidence_labeler` - Confidence scoring
+- `relation_type_labeler` - Relation type classification
 
-**Taxonomy Classifiers (Stage 6):**
+**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.
 
+## Entity Database
+
+The library includes an **entity embedding database** for fast entity qualification using vector similarity search. It stores records from authoritative sources (GLEIF, SEC, Companies House, Wikidata) with 768-dimensional embeddings for semantic matching.
+
+**Quick start:**
+```bash
+corp-extractor db download              # Download pre-built database
+corp-extractor db search "Microsoft"    # Search organizations
+corp-extractor db search-people "Tim Cook"  # Search people
+```
+
+For comprehensive documentation including schema, CLI reference, Python API, and build instructions, see **[ENTITY_DATABASE.md](./ENTITY_DATABASE.md)**.
+
+## 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 (SPARQL) | Variable | Wikidata QID | executive, politician, athlete, artist, academic, scientist, journalist, entrepreneur, activist |
+| Wikidata (Dump) | All humans with enwiki | Wikidata QID | Classified from positions (P39) and occupations (P106) |
+
+**Date Fields**: All importers now include `from_date` and `to_date` where available:
+- **GLEIF**: LEI registration date
+- **SEC Edgar**: First SEC filing date
+- **Companies House**: Incorporation and dissolution dates
+- **Wikidata Orgs**: Inception (P571) and dissolution (P576) dates
+- **Wikidata People**: Position start (P580) and end (P582) dates
+
+**Note**: The same person can have multiple records with different role/org combinations (unique on `source_id + role + org`). Organizations discovered during people import are automatically inserted into the organizations table with `known_for_org_id` foreign key linking people to their organizations.
+
+### 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
+corp-extractor db import-people --type executive --skip-existing  # Skip existing records
+corp-extractor db import-people --type executive --enrich-dates   # Fetch role start/end dates
+
+# Import from Wikidata dump (v0.9.1) - avoids SPARQL timeouts
+corp-extractor db import-wikidata-dump --download --limit 50000   # Downloads ~100GB dump
+corp-extractor db import-wikidata-dump --dump /path/to/dump.bz2 --people --no-orgs  # Local dump
+
+# 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.
@@ -575,7 +773,7 @@ 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**: Each triple scored for groundedness in source text
+2. **Quality Scoring**: Each triple scored via semantic similarity + GLiNER2 entity recognition
 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

corp_extractor-0.9.3.dist-info/RECORD

@@ -0,0 +1,79 @@
+statement_extractor/__init__.py,sha256=vOJFsK6wNOoBvGYOvIKsseaqpFR8vNg_XPH-r8SmLas,3215
+statement_extractor/canonicalization.py,sha256=ZMLs6RLWJa_rOJ8XZ7PoHFU13-zeJkOMDnvK-ZaFa5s,5991
+statement_extractor/cli.py,sha256=l4YcqKmtks6exMAIHSUw_ukWGZ4x-v_V_Gnm-wOGc3g,106464
+statement_extractor/extractor.py,sha256=m10na6I2iU1GwokQTxodePttYgigHykoss5LWrE8JOQ,38418
+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=rBotCX2hRTMW4MXXkkWYv4JctP0HQR0NSJSlBcNhsF0,12302
+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=3xCvbCeqC6GR3XgVow7MAXg46ZPDYfDX8it93Xikw5w,13295
+statement_extractor/database/models.py,sha256=4aLs5tp2QTAd9vAyPf80EUoHypd_K0jELcY4J51iaNw,10563
+statement_extractor/database/resolver.py,sha256=_fTITarFmAYOtuRbOos48ou_aqX4yJC0K2csdLbIktI,7202
+statement_extractor/database/store.py,sha256=FPyfC6KjD6pjfU2jccVEvsAcCtfqMdwVJuS7aqCNrKA,112320
+statement_extractor/database/importers/__init__.py,sha256=acIoX_BPdXv2DOMFyVbFZPDGNWp2s1FpC774loTqL5I,1121
+statement_extractor/database/importers/companies_house.py,sha256=b5OMFtoHhkPgoGK08ThQn9BtTu9uC_dYzBVpC10xT4U,20252
+statement_extractor/database/importers/companies_house_officers.py,sha256=QDFA0FzqDx9p6VjRrB7o4BE3e30l7i0ML_ktntsB-kA,15565
+statement_extractor/database/importers/gleif.py,sha256=sw4YYROD6wi7IbBEKGCn8kko0nOYbKOyukDJKGQp17Q,20200
+statement_extractor/database/importers/sec_edgar.py,sha256=0nnhnOrf5d1wR9PGjl8AuNOnp4mfmEtopjkgUY_PLQc,13738
+statement_extractor/database/importers/sec_form4.py,sha256=ZoV-oyNhG5AOUm4u9hemmRI5KnpNs3Gw_dfisjkD3zU,18234
+statement_extractor/database/importers/wikidata.py,sha256=tRj4kEMVIq7sRXxjyxj-scl8eXybkrLVvyNDYV2T5lg,39572
+statement_extractor/database/importers/wikidata_dump.py,sha256=GSLn_BV4h-Efms2tp_eYyhqSJsRFjnZzyqgaUCDmyVY,77903
+statement_extractor/database/importers/wikidata_people.py,sha256=s4AB2pQLK2qHK9X5BLoW-II3qZBbJG4zbU3Ro4FBT9o,43157
+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=R_RwEdVeVQBYZHvjkVA0ShAWr8x618VrO9dkYWXvifI,4771
+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=OJOK0ral_jskrSxx6nCc3TB6JlVYaC5HI2eYXr9dhMQ,2971
+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=Wpp2OtZ5inhqbtEcblWdcES7g7lA-FVjqjz6Jq7hqzo,3329
+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=evAdyH5oOCNM_ILGZNS1mov3lM4D3mCvr5hzsjaB0Bs,6136
+statement_extractor/pipeline/orchestrator.py,sha256=qH6rD4_wI_kZ_e8NeIv2XYHUA07ldogFewFsZeRQVxw,16687
+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=xC661iFtnhIxtZLTwuCc-0rFV1q2V3hCTV-uOaILsOA,21622
+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=yDwKJVniMj4YwjR4Rm6MALDk633H5qcKcxa2xOLh9LI,21999
+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=nc7oTFjEBuPiprjXKeFRiMYM6tNicMNum_xQ9LSgEOg,14756
+statement_extractor/plugins/qualifiers/gleif.py,sha256=zHzC9eOt0R9Z56n0CXgTF7POJqu6v03SRmiJLmv8OGE,6104
+statement_extractor/plugins/qualifiers/person.py,sha256=EN1T0G9NT6wOeIGljzZql11o63BujaHzK44yRqMTiRk,29034
+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=5qjxeHznuAA9hL8EbUDDGQ3N2gYLmtg0hv9BsLWzfMk,9971
+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-0.9.3.dist-info/METADATA,sha256=Ps8LucareMigmuhXiPIDUXPgsWp5F7noVYT7VbTrSZA,29633
+corp_extractor-0.9.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+corp_extractor-0.9.3.dist-info/entry_points.txt,sha256=i0iKFqPIusvb-QTQ1zNnFgAqatgVah-jIhahbs5TToQ,115
+corp_extractor-0.9.3.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 (