pranjalparmar/fastdocparse - 10 Help Wanted Issues

Open Issues Need Help

Raise TypeError instead of ValueError for a type check in schema.py validator (ruff TRY004) about 2 hours ago

good first issue

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Add a demo screenshot/GIF to the README about 2 hours ago

documentation help wanted

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Build a benchmark comparing extraction accuracy against a vision-LLM baseline (e.g. Sparrow) about 3 hours ago

enhancement help wanted

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Simplify two needless boolean if/else returns in grounding.py (ruff SIM103) about 3 hours ago

good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Silence ruff's B008 false positive on Typer Option()/Argument() defaults in cli.py about 3 hours ago

help wanted good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Modernize type hints to PEP 585/604 across the codebase (ruff UP006, UP035, UP045, FA100, UP037) about 3 hours ago

enhancement help wanted

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Replace bare except-Exception blocks with narrower exception handling (ruff BLE001 / S110 / S112) about 3 hours ago

help wanted good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Make datetime.strptime calls timezone-aware (ruff DTZ007) about 3 hours ago

help wanted good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Add explicit check= argument to subprocess.run in tests (ruff PLW1510) about 3 hours ago

help wanted good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction

Sort imports across src/ and tests/ (ruff I001) about 3 hours ago

help wanted good first issue

pranjalparmar/fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Python

#document-extraction#document-processing#invoice-extraction#llm#ocr#ollama#openai#pdf#python#structured-data-extraction