Spaces:

akshayyy1
/

vector-auditor

Running

App Files Files Community

vector-auditor / src

216 kB

Ctrl+K

Ctrl+K

3 contributors

History: 99 commits

AkshayM

fix: job_queue remove relative import for DLQ auto-retry

f731db5 7 days ago

agents
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
api
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
database
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
models
Add max_tokens parameter to NexAGI endpoint 4 months ago
services
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
vectorstore
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
__init__.py

84 Bytes
fix models.py: match Neon schema varchar sizes, add email unique constraint 4 months ago
bootstrap.py

5.03 kB
fix: 15 critical/high bugs across codebase 4 months ago
config.py

6.32 kB
fix: reduce max_citations_total=10, retrieve_k=15, rerank_top_k=10 + filter chunks <50 chars 4 months ago
job_queue.py

10.7 kB
fix: job_queue remove relative import for DLQ auto-retry 7 days ago
observability.py

6.83 kB
feat: 10 free upgrades — streaming upload, cache invalidation, hybrid search, ONNX reranker, SQLAlchemy pool tuning, batch embed cache, semantic chunking, Prometheus histograms, DLQ auto-retry, structured logging+OTel 7 days ago
shutdown.py

3.17 kB
fix: 15 critical/high bugs across codebase 4 months ago
version.py

86 Bytes
fix models.py: match Neon schema varchar sizes, add email unique constraint 4 months ago