perditioinc/reporium-ingestion
reporium-ingestion
Local data ingestion and analysis scripts for Reporium : fetch, process, and generate embeddings for repositories, communicating with Reporium API. AI-native analysis, embeddings, scraping, tagging. Pushes updates to API. Standalone and private by default.
Builder
perditioinc
perditioinc • individual
Stars
1
Repository stars
Forks
0
Repository forks
Open Issues
0
Activity Score
0/100
50 commits in 30d
Created
—
README Summary
Reporium-ingestion is a Python-based local data processing system that fetches, analyzes, and generates embeddings for code repositories. It provides AI-native analysis capabilities including scraping, tagging, and embedding generation while maintaining standalone and private-by-default operation. The system communicates with the Reporium API to push processed updates and repository insights.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Skill Areas
Recent Activity
Updated 14 days ago
7 Days
0
30 Days
50
90 Days
50
fix(fetcher): fetch languages in QUICK mode when uncached (#31) * feat(ci): add manual ingestion workflow dispatch Adds workflow_dispatch trigger to run the main ingestion pipeline in quick/weekly/full mode without waiting for scheduled runs. Full mode fetches GitHub topics + READMEs for all repos, which restores granular tags like specific technology names that the taxonomy enricher doesn't generate. Also supports fix_repos input to re-ingest specific repos by name. Co-Authored-By: Claude S
kimmymakesmoves • Mar 26, 2026
feat(ci): add manual ingestion workflow dispatch (#30) Adds workflow_dispatch trigger to run the main ingestion pipeline in quick/weekly/full mode without waiting for scheduled runs. Full mode fetches GitHub topics + READMEs for all repos, which restores granular tags like specific technology names that the taxonomy enricher doesn't generate. Also supports fix_repos input to re-ingest specific repos by name. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
kimmymakesmoves • Mar 25, 2026
fix(ingestion): include stargazers_count in API payload for built repos (#29) * fix: align ai_enricher with production schema (KAN-40) The enricher was writing to JSONB columns (skill_areas, industries, use_cases, modalities, ai_trends, deployment_context, maturity_level, quality_assessment, dependencies) that have never existed in production. Migration 014 also dropped dependencies. This caused immediate failure on any enrichment run against the live DB. Changes: - Remove SELECT of dependenc
kimmymakesmoves • Mar 25, 2026
Quality
prototype- Quality
- medium
- Maturity
- prototype
Categories
PM Skills
Languages
Timeline
- Project created
- —
- Forked
- —
- Your last push
- 18 days ago
- Upstream last push
- —
- Tracked since
- Mar 30, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…