super-document-processor 0.1.3__tar.gz → 0.1.5__tar.gz

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: super-document-processor
-Version: 0.1.3
+Version: 0.1.5
 Summary: High-fidelity multi-format document parsing and chunking engine for RAG pipelines
 Author: Cinderfox
 License: MIT
@@ -26,7 +26,7 @@ Requires-Dist: python-docx==1.2.0
 Requires-Dist: python-pptx==1.0.2
 Requires-Dist: extract-msg==0.56.1
 Requires-Dist: lxml==6.1.3
-Requires-Dist: aspose-slides==26.7.0
+Requires-Dist: aspose-slides==26.8.0
 Requires-Dist: python-dotenv==1.2.3
 Requires-Dist: fastapi==0.141.1
 Requires-Dist: uvicorn==0.52.4
@@ -58,24 +58,25 @@ Available as a **Python library**, **CLI tool**, and **FastAPI microservice** (w
 
 ## Quickstart
 
-### 1. Local Setup
+### 1. Install via PyPI
+```bash
+pip install super-document-processor
+```
+
+### 2. Or Local Clone
 ```bash
 git clone https://github.com/Cinderfox/Super-Document-Processor.git
 cd Super-Document-Processor
 
-# Setup environment
 python -m venv .venv
 source .venv/bin/activate  # On Windows: .\.venv\Scripts\activate
 pip install -r requirements.txt
-
-# Configure environment (optional, required only for Vision LLMs)
 cp .env.example .env
 ```
 
-### 2. Docker Setup
+### 3. Docker
 ```bash
-docker build -t super-document-processor:latest .
-docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data super-document-processor:latest
+docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data cinderfox/super-document-processor:latest
 ```
 
 ---
@@ -132,7 +133,7 @@ collector.clear()
 Export PowerPoint slides directly to SVGs or PNGs:
 
 ```python
-from utils.pptx_converter import convert_pptx, create_pptx_render_zip
+from super_document_processor import convert_pptx, create_pptx_render_zip
 
 # 1. Convert all slides to SVGs (returns list of clean SVG strings)
 res = convert_pptx("presentation.pptx", format="svg")
@@ -254,6 +255,12 @@ curl -X POST "http://localhost:8000/convert/pptx?format=png&as_zip=true" \
 
 #### Convert Mounted Volume Path via JSON Body
 ```bash
+# Convert specific slide to PNG
+curl -X POST "http://localhost:8000/convert/pptx" \
+     -H "Content-Type: application/json" \
+     -d '{"file_path": "/data/presentation.pptx", "slide": 1, "format": "png"}' -o slide_1.png
+
+# Convert all slides to SVG
 curl -X POST "http://localhost:8000/convert/pptx" \
      -H "Content-Type: application/json" \
      -d '{"file_path": "/data/presentation.pptx", "format": "svg"}'
@@ -365,9 +372,11 @@ docker compose up -d
 
 | Variable | Default | Description |
 |---|---|---|
+| `MAX_WORKERS` | `3` | Max concurrent worker threads for slide rendering, image extraction, and VLM calls |
 | `PORT` | `8000` | HTTP port when running in server mode |
+| `JOBS_DIR` | `/data/jobs` (or `./data/jobs`) | Storage directory for asynchronous background job results |
 | `OPENAI_API_KEY` | *None* | API key for Vision LLM extraction |
-| `OPENAI_BASE_URL` | `https://api.openai.com/v1` | Custom gateway URL (LiteLLM, Ollama, Gemini, Groq, etc.) |
+| `OPENAI_BASE_URL` | *None* | Gateway URL (e.g. `https://api.openai.com/v1`, LiteLLM, Ollama, etc.) |
 
 ---
 

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/README.md

@@ -20,24 +20,25 @@ Available as a **Python library**, **CLI tool**, and **FastAPI microservice** (w
 
 ## Quickstart
 
-### 1. Local Setup
+### 1. Install via PyPI
+```bash
+pip install super-document-processor
+```
+
+### 2. Or Local Clone
 ```bash
 git clone https://github.com/Cinderfox/Super-Document-Processor.git
 cd Super-Document-Processor
 
-# Setup environment
 python -m venv .venv
 source .venv/bin/activate  # On Windows: .\.venv\Scripts\activate
 pip install -r requirements.txt
-
-# Configure environment (optional, required only for Vision LLMs)
 cp .env.example .env
 ```
 
-### 2. Docker Setup
+### 3. Docker
 ```bash
-docker build -t super-document-processor:latest .
-docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data super-document-processor:latest
+docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data cinderfox/super-document-processor:latest
 ```
 
 ---
@@ -94,7 +95,7 @@ collector.clear()
 Export PowerPoint slides directly to SVGs or PNGs:
 
 ```python
-from utils.pptx_converter import convert_pptx, create_pptx_render_zip
+from super_document_processor import convert_pptx, create_pptx_render_zip
 
 # 1. Convert all slides to SVGs (returns list of clean SVG strings)
 res = convert_pptx("presentation.pptx", format="svg")
@@ -216,6 +217,12 @@ curl -X POST "http://localhost:8000/convert/pptx?format=png&as_zip=true" \
 
 #### Convert Mounted Volume Path via JSON Body
 ```bash
+# Convert specific slide to PNG
+curl -X POST "http://localhost:8000/convert/pptx" \
+     -H "Content-Type: application/json" \
+     -d '{"file_path": "/data/presentation.pptx", "slide": 1, "format": "png"}' -o slide_1.png
+
+# Convert all slides to SVG
 curl -X POST "http://localhost:8000/convert/pptx" \
      -H "Content-Type: application/json" \
      -d '{"file_path": "/data/presentation.pptx", "format": "svg"}'
@@ -327,9 +334,11 @@ docker compose up -d
 
 | Variable | Default | Description |
 |---|---|---|
+| `MAX_WORKERS` | `3` | Max concurrent worker threads for slide rendering, image extraction, and VLM calls |
 | `PORT` | `8000` | HTTP port when running in server mode |
+| `JOBS_DIR` | `/data/jobs` (or `./data/jobs`) | Storage directory for asynchronous background job results |
 | `OPENAI_API_KEY` | *None* | API key for Vision LLM extraction |
-| `OPENAI_BASE_URL` | `https://api.openai.com/v1` | Custom gateway URL (LiteLLM, Ollama, Gemini, Groq, etc.) |
+| `OPENAI_BASE_URL` | *None* | Gateway URL (e.g. `https://api.openai.com/v1`, LiteLLM, Ollama, etc.) |
 
 ---
 

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "super-document-processor"
-version = "0.1.3"
+version = "0.1.5"
 description = "High-fidelity multi-format document parsing and chunking engine for RAG pipelines"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -43,7 +43,7 @@ dependencies = [
     "python-pptx==1.0.2",
     "extract-msg==0.56.1",
     "lxml==6.1.3",
-    "aspose-slides==26.7.0",
+    "aspose-slides==26.8.0",
     "python-dotenv==1.2.3",
     "fastapi==0.141.1",
     "uvicorn==0.52.4",

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/super_document_processor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: super-document-processor
-Version: 0.1.3
+Version: 0.1.5
 Summary: High-fidelity multi-format document parsing and chunking engine for RAG pipelines
 Author: Cinderfox
 License: MIT
@@ -26,7 +26,7 @@ Requires-Dist: python-docx==1.2.0
 Requires-Dist: python-pptx==1.0.2
 Requires-Dist: extract-msg==0.56.1
 Requires-Dist: lxml==6.1.3
-Requires-Dist: aspose-slides==26.7.0
+Requires-Dist: aspose-slides==26.8.0
 Requires-Dist: python-dotenv==1.2.3
 Requires-Dist: fastapi==0.141.1
 Requires-Dist: uvicorn==0.52.4
@@ -58,24 +58,25 @@ Available as a **Python library**, **CLI tool**, and **FastAPI microservice** (w
 
 ## Quickstart
 
-### 1. Local Setup
+### 1. Install via PyPI
+```bash
+pip install super-document-processor
+```
+
+### 2. Or Local Clone
 ```bash
 git clone https://github.com/Cinderfox/Super-Document-Processor.git
 cd Super-Document-Processor
 
-# Setup environment
 python -m venv .venv
 source .venv/bin/activate  # On Windows: .\.venv\Scripts\activate
 pip install -r requirements.txt
-
-# Configure environment (optional, required only for Vision LLMs)
 cp .env.example .env
 ```
 
-### 2. Docker Setup
+### 3. Docker
 ```bash
-docker build -t super-document-processor:latest .
-docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data super-document-processor:latest
+docker run -d --name doc-processor -p 8000:8000 -v ${PWD}/data:/data cinderfox/super-document-processor:latest
 ```
 
 ---
@@ -132,7 +133,7 @@ collector.clear()
 Export PowerPoint slides directly to SVGs or PNGs:
 
 ```python
-from utils.pptx_converter import convert_pptx, create_pptx_render_zip
+from super_document_processor import convert_pptx, create_pptx_render_zip
 
 # 1. Convert all slides to SVGs (returns list of clean SVG strings)
 res = convert_pptx("presentation.pptx", format="svg")
@@ -254,6 +255,12 @@ curl -X POST "http://localhost:8000/convert/pptx?format=png&as_zip=true" \
 
 #### Convert Mounted Volume Path via JSON Body
 ```bash
+# Convert specific slide to PNG
+curl -X POST "http://localhost:8000/convert/pptx" \
+     -H "Content-Type: application/json" \
+     -d '{"file_path": "/data/presentation.pptx", "slide": 1, "format": "png"}' -o slide_1.png
+
+# Convert all slides to SVG
 curl -X POST "http://localhost:8000/convert/pptx" \
      -H "Content-Type: application/json" \
      -d '{"file_path": "/data/presentation.pptx", "format": "svg"}'
@@ -365,9 +372,11 @@ docker compose up -d
 
 | Variable | Default | Description |
 |---|---|---|
+| `MAX_WORKERS` | `3` | Max concurrent worker threads for slide rendering, image extraction, and VLM calls |
 | `PORT` | `8000` | HTTP port when running in server mode |
+| `JOBS_DIR` | `/data/jobs` (or `./data/jobs`) | Storage directory for asynchronous background job results |
 | `OPENAI_API_KEY` | *None* | API key for Vision LLM extraction |
-| `OPENAI_BASE_URL` | `https://api.openai.com/v1` | Custom gateway URL (LiteLLM, Ollama, Gemini, Groq, etc.) |
+| `OPENAI_BASE_URL` | *None* | Gateway URL (e.g. `https://api.openai.com/v1`, LiteLLM, Ollama, etc.) |
 
 ---
 

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/super_document_processor.egg-info/requires.txt

@@ -3,7 +3,7 @@ python-docx==1.2.0
 python-pptx==1.0.2
 extract-msg==0.56.1
 lxml==6.1.3
-aspose-slides==26.7.0
+aspose-slides==26.8.0
 python-dotenv==1.2.3
 fastapi==0.141.1
 uvicorn==0.52.4

{super_document_processor-0.1.3 → super_document_processor-0.1.5}/utils/vlm.py

@@ -1,3 +1,4 @@
+import os
 import base64
 import json
 import logging
@@ -61,8 +62,14 @@ def is_auth_error(error_msg: str) -> bool:
     return any(indicator in err_lower for indicator in auth_indicators)
 
 def generate_image_description(image_bytes, model=None, max_retries=3, retry_delay=2):
-    base_url = (OPENAI_BASE_URL).rstrip("/")
-    api_key = OPENAI_API_KEY
+    raw_base_url = os.getenv("OPENAI_BASE_URL") or OPENAI_BASE_URL
+    if not raw_base_url:
+        raise ValueError(
+            "Cannot process images: OPENAI_BASE_URL is not set in the environment.\n"
+            "Please set OPENAI_BASE_URL (e.g. 'https://api.openai.com/v1' or custom gateway) or disable image processing."
+        )
+    base_url = raw_base_url.rstrip("/")
+    api_key = os.getenv("OPENAI_API_KEY") or OPENAI_API_KEY
 
     is_local = "localhost" in base_url or "127.0.0.1" in base_url
     if not api_key and not is_local: