pdf-to-text-chroma-search esokullu · COMPLETED
Python scripts that converts PDF files to text, splits them into chunks, and stores their vector representations using GPT4All embeddings in a Chroma DB. It also provides a script to query the Chroma DB for similarity search based on user input.
github.com/esokullu/pdf-to-text-chroma-search · ★ 0 · Forks 0 · Size 4 KB
SUMMARY
Technologies 2
Scored 2
Observed 2
Practices 6
Evidence 2
Skips 0
COVERAGE
Analyzed 4 files · 4 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
2 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2023-10-23
Last commit 2023-10-23
Active months 1
Commits 4