docintel-platform 1.2.0__tar.gz → 1.4.0__tar.gz

{docintel_platform-1.2.0/src/docintel_platform.egg-info → docintel_platform-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docintel-platform
-Version: 1.2.0
+Version: 1.4.0
 Summary: Enterprise document intelligence API for PDF compliance, multi-format extraction, structuring, and summarization.
 Author: Babandeep Singh
 License-Expression: MIT
@@ -40,17 +40,19 @@ Requires-Dist: fakeredis>=2.26.2; extra == "dev"
 Requires-Dist: prometheus-client>=0.21.0; extra == "dev"
 Requires-Dist: python-docx>=1.1.2; extra == "dev"
 Requires-Dist: openpyxl>=3.1.5; extra == "dev"
+Requires-Dist: python-pptx>=1.0.2; extra == "dev"
 Provides-Extra: documents
 Requires-Dist: python-docx>=1.1.2; extra == "documents"
 Requires-Dist: openpyxl>=3.1.5; extra == "documents"
+Requires-Dist: python-pptx>=1.0.2; extra == "documents"
+Provides-Extra: pii
+Requires-Dist: presidio-analyzer>=2.2.354; extra == "pii"
+Requires-Dist: spacy>=3.7.0; extra == "pii"
 Provides-Extra: ocr
 Requires-Dist: easyocr>=1.7.2; extra == "ocr"
-Requires-Dist: presidio-analyzer>=2.2.354; extra == "ocr"
-Requires-Dist: spacy>=3.7.0; extra == "ocr"
 Requires-Dist: opencv-python-headless>=4.10.0; extra == "ocr"
-Requires-Dist: torch>=2.4.1; extra == "ocr"
 Provides-Extra: ui
-Requires-Dist: gradio>=4.44.0; extra == "ui"
+Requires-Dist: gradio<6,>=5.7.1; extra == "ui"
 Requires-Dist: requests>=2.32.3; extra == "ui"
 Provides-Extra: llm
 Requires-Dist: openai>=1.54.0; extra == "llm"
@@ -65,10 +67,9 @@ Requires-Dist: PyJWT>=2.9.0; extra == "auth"
 Requires-Dist: cryptography>=43.0.0; extra == "auth"
 Provides-Extra: all
 Requires-Dist: easyocr>=1.7.2; extra == "all"
+Requires-Dist: opencv-python-headless>=4.10.0; extra == "all"
 Requires-Dist: presidio-analyzer>=2.2.354; extra == "all"
 Requires-Dist: spacy>=3.7.0; extra == "all"
-Requires-Dist: opencv-python-headless>=4.10.0; extra == "all"
-Requires-Dist: torch>=2.4.1; extra == "all"
 Requires-Dist: openai>=1.54.0; extra == "all"
 Requires-Dist: redis>=5.0.8; extra == "all"
 Requires-Dist: rq>=1.16.2; extra == "all"
@@ -77,9 +78,10 @@ Requires-Dist: prometheus-client>=0.21.0; extra == "all"
 Requires-Dist: flask-limiter>=3.8.0; extra == "all"
 Requires-Dist: PyJWT>=2.9.0; extra == "all"
 Requires-Dist: cryptography>=43.0.0; extra == "all"
-Requires-Dist: gradio>=4.44.0; extra == "all"
+Requires-Dist: gradio<6,>=5.7.1; extra == "all"
 Requires-Dist: python-docx>=1.1.2; extra == "all"
 Requires-Dist: openpyxl>=3.1.5; extra == "all"
+Requires-Dist: python-pptx>=1.0.2; extra == "all"
 
 # Document Intelligence Platform
 
@@ -90,21 +92,31 @@ Requires-Dist: openpyxl>=3.1.5; extra == "all"
 
 Enterprise document intelligence API: PDF compliance (OCR, PII, redaction), LLM structuring, and multi-format text workflows (Word, Excel, CSV, plain text).
 
-**Version:** 1.2.0 | **PyPI:** [docintel-platform](https://pypi.org/project/docintel-platform/)
+**Version:** 1.4.0 | **PyPI:** [docintel-platform](https://pypi.org/project/docintel-platform/)
 
 ---
 
 ## Quick start
 
-**Docker (API + Gradio UI + worker):**
+**Docker (slim core, optional UI and OCR):**
 
 ```bash
 git clone https://github.com/baban9/document-intelligence-platform.git
 cd document-intelligence-platform
 cp .env.example .env   # optional: ports, LLM key, auth
-make docker-up
+make docker-up         # redis + API + worker (~2 min build, no PyTorch)
+make docker-up-ui      # add Gradio when API is healthy
 ```
 
+| Command | What starts |
+|---------|-------------|
+| `make docker-up` | Redis, slim API, slim worker (documents, PII text, digital PDF) |
+| `make docker-up-ui` | Gradio UI (`--profile ui`) |
+| `make docker-up-ocr` | Rebuild with CPU-only OCR for scanned PDFs (no NVIDIA) |
+| `make docker-up-full` | OCR stack + UI |
+
+Slim image skips PyTorch and EasyOCR (~400MB+). Scanned PDF OCR is opt-in via `make docker-up-ocr`.
+
 | Service | URL |
 |---------|-----|
 | API | http://127.0.0.1:5000 |
@@ -112,14 +124,14 @@ make docker-up
 | Gradio UI | http://127.0.0.1:7860 |
 | Health | http://127.0.0.1:5000/health |
 
-Gradio includes a **Document process** tab (unified pipeline). It needs the API plus a Redis worker (`worker` service in compose, or `make run-worker` locally).
+Gradio includes a **Document process** tab (unified pipeline) and a **Document integrity** tab (gap and consistency checks). It needs the API plus a Redis worker (`worker` service in compose, or `make run-worker` locally).
 
 **pip install:**
 
 ```bash
 pip install docintel-platform
 pip install "docintel-platform[all]"        # OCR, LLM, jobs, auth, UI, office formats
-pip install "docintel-platform[documents]"  # Word and Excel only
+pip install "docintel-platform[documents]"  # Word, Excel, and PowerPoint
 ```
 
 **Python client:**
@@ -141,13 +153,13 @@ report = client.process_document("policy.docx", include_pii=True)
 | PDF annotate | `POST /v1/pdf/annotate` | Regex highlight, redact, markup |
 | PDF PII scan | `POST /v1/pdf/detect-sensitive` | Presidio + OCR for scanned PDFs |
 | PDF structure | `POST /v1/pdf/structure` | OCR + LLM curated PDF (needs LLM key) |
-| Documents | `POST /v1/documents/*` | Identify, extract, classify, summarize, PII, compare, **process** |
+| Documents | `POST /v1/documents/*` | Identify, extract, classify, summarize, PII, compare, **process**, **ingest** (S3), **analyze-integrity** |
 | Text | `POST /v1/text/summarize` | TextRank extractive summary |
 | Batch | `POST /v1/batch` | Async summarize, classify, detect_pii, process |
 | Jobs | `GET /v1/jobs/{id}` | Poll async work (`?async=true`; default in Docker when Redis is up) |
 | Ops | `GET /health`, `GET /metrics` | Health and Prometheus-friendly metrics |
 
-**Supported uploads (text workflows):** PDF, DOCX, XLSX, CSV, JSON, TXT, MD.
+**Supported uploads (text workflows):** PDF, DOCX, XLSX, PPTX, CSV, JSON, TXT, MD.
 
 **PDF-only routes** (annotate, sensitive, structure) return HTTP 415 for other types. Use `/v1/documents/extract-text` or `/v1/documents/process` for office files.
 
@@ -169,6 +181,11 @@ curl -X POST http://127.0.0.1:5000/v1/documents/process \
 # Async: add ?async=true, then poll /v1/jobs/<job_id>
 curl -X POST "http://127.0.0.1:5000/v1/documents/process?async=true" \
   -F "file=@policy.docx"
+
+# Document integrity analysis (placeholders, broken refs, drift, number mismatch)
+curl -X POST http://127.0.0.1:5000/v1/documents/analyze-integrity \
+  -H "Content-Type: application/json" \
+  -d '{"text": "See Section 9.2. Total budget: $1M. Total budget: $900K. TBD"}'
 ```
 
 ---
@@ -177,9 +194,11 @@ curl -X POST "http://127.0.0.1:5000/v1/documents/process?async=true" \
 
 ```bash
 make setup              # venv + dev deps
+make setup-hooks        # block Cursor agent co-author trailers on commit
 make setup-ocr          # EasyOCR, Presidio, spaCy model
 make setup-llm          # OpenAI client (structure endpoint)
 make setup-ui           # Gradio
+make run-redis          # Redis for async jobs (Docker, port 6379)
 make run                # API on :5000
 make run-worker         # RQ worker (separate terminal, needs Redis)
 make run-ui             # Gradio on :7860
@@ -187,6 +206,8 @@ make test
 make eval               # offline quality report (summary, classify, process, PII)
 ```
 
+Async routes and the Gradio integrity tab need Redis. Start it once with `make run-redis` before `make run-worker`.
+
 Copy `.env.example` to `.env` for `DOCINTEL_LLM_API_KEY`, auth keys, Redis, and S3. See comments in that file for all variables.
 
 ---
@@ -199,6 +220,7 @@ Copy `.env.example` to `.env` for `DOCINTEL_LLM_API_KEY`, auth keys, Redis, and
 | [docs/PLATFORM.md](docs/PLATFORM.md) | Jobs, auth, storage, ops layout |
 | [docs/PRODUCTION.md](docs/PRODUCTION.md) | Checklist, latency, failure modes |
 | [docs/ROADMAP.md](docs/ROADMAP.md) | Milestones and history |
+| [docs/WEBHOOKS.md](docs/WEBHOOKS.md) | Async callbacks and S3 ingest |
 | [docs/adr/](docs/adr/) | Architecture decision records |
 
 ---

{docintel_platform-1.2.0 → docintel_platform-1.4.0}/README.md

@@ -7,21 +7,31 @@
 
 Enterprise document intelligence API: PDF compliance (OCR, PII, redaction), LLM structuring, and multi-format text workflows (Word, Excel, CSV, plain text).
 
-**Version:** 1.2.0 | **PyPI:** [docintel-platform](https://pypi.org/project/docintel-platform/)
+**Version:** 1.4.0 | **PyPI:** [docintel-platform](https://pypi.org/project/docintel-platform/)
 
 ---
 
 ## Quick start
 
-**Docker (API + Gradio UI + worker):**
+**Docker (slim core, optional UI and OCR):**
 
 ```bash
 git clone https://github.com/baban9/document-intelligence-platform.git
 cd document-intelligence-platform
 cp .env.example .env   # optional: ports, LLM key, auth
-make docker-up
+make docker-up         # redis + API + worker (~2 min build, no PyTorch)
+make docker-up-ui      # add Gradio when API is healthy
 ```
 
+| Command | What starts |
+|---------|-------------|
+| `make docker-up` | Redis, slim API, slim worker (documents, PII text, digital PDF) |
+| `make docker-up-ui` | Gradio UI (`--profile ui`) |
+| `make docker-up-ocr` | Rebuild with CPU-only OCR for scanned PDFs (no NVIDIA) |
+| `make docker-up-full` | OCR stack + UI |
+
+Slim image skips PyTorch and EasyOCR (~400MB+). Scanned PDF OCR is opt-in via `make docker-up-ocr`.
+
 | Service | URL |
 |---------|-----|
 | API | http://127.0.0.1:5000 |
@@ -29,14 +39,14 @@ make docker-up
 | Gradio UI | http://127.0.0.1:7860 |
 | Health | http://127.0.0.1:5000/health |
 
-Gradio includes a **Document process** tab (unified pipeline). It needs the API plus a Redis worker (`worker` service in compose, or `make run-worker` locally).
+Gradio includes a **Document process** tab (unified pipeline) and a **Document integrity** tab (gap and consistency checks). It needs the API plus a Redis worker (`worker` service in compose, or `make run-worker` locally).
 
 **pip install:**
 
 ```bash
 pip install docintel-platform
 pip install "docintel-platform[all]"        # OCR, LLM, jobs, auth, UI, office formats
-pip install "docintel-platform[documents]"  # Word and Excel only
+pip install "docintel-platform[documents]"  # Word, Excel, and PowerPoint
 ```
 
 **Python client:**
@@ -58,13 +68,13 @@ report = client.process_document("policy.docx", include_pii=True)
 | PDF annotate | `POST /v1/pdf/annotate` | Regex highlight, redact, markup |
 | PDF PII scan | `POST /v1/pdf/detect-sensitive` | Presidio + OCR for scanned PDFs |
 | PDF structure | `POST /v1/pdf/structure` | OCR + LLM curated PDF (needs LLM key) |
-| Documents | `POST /v1/documents/*` | Identify, extract, classify, summarize, PII, compare, **process** |
+| Documents | `POST /v1/documents/*` | Identify, extract, classify, summarize, PII, compare, **process**, **ingest** (S3), **analyze-integrity** |
 | Text | `POST /v1/text/summarize` | TextRank extractive summary |
 | Batch | `POST /v1/batch` | Async summarize, classify, detect_pii, process |
 | Jobs | `GET /v1/jobs/{id}` | Poll async work (`?async=true`; default in Docker when Redis is up) |
 | Ops | `GET /health`, `GET /metrics` | Health and Prometheus-friendly metrics |
 
-**Supported uploads (text workflows):** PDF, DOCX, XLSX, CSV, JSON, TXT, MD.
+**Supported uploads (text workflows):** PDF, DOCX, XLSX, PPTX, CSV, JSON, TXT, MD.
 
 **PDF-only routes** (annotate, sensitive, structure) return HTTP 415 for other types. Use `/v1/documents/extract-text` or `/v1/documents/process` for office files.
 
@@ -86,6 +96,11 @@ curl -X POST http://127.0.0.1:5000/v1/documents/process \
 # Async: add ?async=true, then poll /v1/jobs/<job_id>
 curl -X POST "http://127.0.0.1:5000/v1/documents/process?async=true" \
   -F "file=@policy.docx"
+
+# Document integrity analysis (placeholders, broken refs, drift, number mismatch)
+curl -X POST http://127.0.0.1:5000/v1/documents/analyze-integrity \
+  -H "Content-Type: application/json" \
+  -d '{"text": "See Section 9.2. Total budget: $1M. Total budget: $900K. TBD"}'
 ```
 
 ---
@@ -94,9 +109,11 @@ curl -X POST "http://127.0.0.1:5000/v1/documents/process?async=true" \
 
 ```bash
 make setup              # venv + dev deps
+make setup-hooks        # block Cursor agent co-author trailers on commit
 make setup-ocr          # EasyOCR, Presidio, spaCy model
 make setup-llm          # OpenAI client (structure endpoint)
 make setup-ui           # Gradio
+make run-redis          # Redis for async jobs (Docker, port 6379)
 make run                # API on :5000
 make run-worker         # RQ worker (separate terminal, needs Redis)
 make run-ui             # Gradio on :7860
@@ -104,6 +121,8 @@ make test
 make eval               # offline quality report (summary, classify, process, PII)
 ```
 
+Async routes and the Gradio integrity tab need Redis. Start it once with `make run-redis` before `make run-worker`.
+
 Copy `.env.example` to `.env` for `DOCINTEL_LLM_API_KEY`, auth keys, Redis, and S3. See comments in that file for all variables.
 
 ---
@@ -116,6 +135,7 @@ Copy `.env.example` to `.env` for `DOCINTEL_LLM_API_KEY`, auth keys, Redis, and
 | [docs/PLATFORM.md](docs/PLATFORM.md) | Jobs, auth, storage, ops layout |
 | [docs/PRODUCTION.md](docs/PRODUCTION.md) | Checklist, latency, failure modes |
 | [docs/ROADMAP.md](docs/ROADMAP.md) | Milestones and history |
+| [docs/WEBHOOKS.md](docs/WEBHOOKS.md) | Async callbacks and S3 ingest |
 | [docs/adr/](docs/adr/) | Architecture decision records |
 
 ---

{docintel_platform-1.2.0 → docintel_platform-1.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "docintel-platform"
-version = "1.2.0"
+version = "1.4.0"
 description = "Enterprise document intelligence API for PDF compliance, multi-format extraction, structuring, and summarization."
 readme = "README.md"
 license = "MIT"
@@ -50,20 +50,25 @@ dev = [
     "prometheus-client>=0.21.0",
     "python-docx>=1.1.2",
     "openpyxl>=3.1.5",
+    "python-pptx>=1.0.2",
 ]
 documents = [
     "python-docx>=1.1.2",
     "openpyxl>=3.1.5",
+    "python-pptx>=1.0.2",
 ]
-ocr = [
-    "easyocr>=1.7.2",
+pii = [
     "presidio-analyzer>=2.2.354",
     "spacy>=3.7.0",
+]
+# Scanned PDF OCR (EasyOCR). Install CPU torch before this extra in Docker:
+# pip install torch --index-url https://download.pytorch.org/whl/cpu
+ocr = [
+    "easyocr>=1.7.2",
     "opencv-python-headless>=4.10.0",
-    "torch>=2.4.1",
 ]
 ui = [
-    "gradio>=4.44.0",
+    "gradio>=5.7.1,<6",
     "requests>=2.32.3",
 ]
 llm = [
@@ -83,10 +88,9 @@ auth = [
 ]
 all = [
     "easyocr>=1.7.2",
+    "opencv-python-headless>=4.10.0",
     "presidio-analyzer>=2.2.354",
     "spacy>=3.7.0",
-    "opencv-python-headless>=4.10.0",
-    "torch>=2.4.1",
     "openai>=1.54.0",
     "redis>=5.0.8",
     "rq>=1.16.2",
@@ -95,9 +99,10 @@ all = [
     "flask-limiter>=3.8.0",
     "PyJWT>=2.9.0",
     "cryptography>=43.0.0",
-    "gradio>=4.44.0",
+    "gradio>=5.7.1,<6",
     "python-docx>=1.1.2",
     "openpyxl>=3.1.5",
+    "python-pptx>=1.0.2",
 ]
 
 [project.scripts]

{docintel_platform-1.2.0 → docintel_platform-1.4.0}/src/docintel/__init__.py

@@ -2,5 +2,5 @@
 
 from docintel.client import DocintelClient, DocintelError
 
-__version__ = "1.2.0"
+__version__ = "1.4.0"
 __all__ = ["DocintelClient", "DocintelError", "__version__"]

{docintel_platform-1.2.0 → docintel_platform-1.4.0}/src/docintel/capabilities/compliance/__init__.py

@@ -1,13 +1,25 @@
 """Compliance capabilities (PII detection, sensitive PDF scanning)."""
 
+from docintel.capabilities.compliance.integrity import (
+    IntegrityEvidence,
+    IntegrityFinding,
+    IntegrityResult,
+    V1_CHECKS,
+    analyze_document_integrity,
+)
 from docintel.capabilities.compliance.pii import PIIHit, detect_pii_in_text, list_supported_entities, mask_pii_in_text
 from docintel.capabilities.compliance.presets import DEFAULT_PII_ENTITIES, MIN_NATIVE_TEXT_CHARS, OCR_RENDER_SCALE
 
 __all__ = [
     "DEFAULT_PII_ENTITIES",
+    "IntegrityEvidence",
+    "IntegrityFinding",
+    "IntegrityResult",
     "MIN_NATIVE_TEXT_CHARS",
     "OCR_RENDER_SCALE",
     "PIIHit",
+    "V1_CHECKS",
+    "analyze_document_integrity",
     "detect_pii_in_text",
     "list_supported_entities",
     "mask_pii_in_text",