dgarnitz/vectorflow
VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.
PythonApache-2.0
Issues
- 1
Remove Unnecessary dependencies from API
#112 opened by dgarnitz - 4
Add Batch Write into Milvus
#52 opened by dgarnitz - 0
Add support for Jina AI Embeddings
#110 opened by dgarnitz - 0
Add Support for Cohere Embeddings
#109 opened by dgarnitz - 2
Implement Log Aggregation & Searching
#88 opened by dgarnitz - 8
Add integration to salesforce
#16 opened by dgarnitz - 2
Add validator service to API
#81 opened by dgarnitz - 1
Add a duplicate prevention mechanism
#13 opened by dgarnitz - 0
Add RAG search capabilities
#105 opened by dgarnitz - 0
Add top k semantic search endpoint
#104 opened by dgarnitz - 3
Bug: Locally error's are not returned to user
#47 opened by antondubek - 3
Research whether `extract_for_token_limit` needs to be updated to support 1106 models.
#98 opened by leohpark - 1
- 1
Upgrade qdrant upload to be async, multithreaded
#11 opened by dgarnitz - 1
Add Integration to Confluence
#18 opened by dgarnitz - 1
Expose gRPC endpoint for VectorFlow Upload
#25 opened by dgarnitz - 1
Add Airbyte Integration
#74 opened by dgarnitz - 1
Add a Zapier Integration for the Managed Service
#71 opened by dgarnitz - 1
Add support for Vector Database namespaces
#38 opened by dgarnitz - 10
Swap Flask API for FastAPI
#78 opened by dgarnitz - 1
Add a reliability mechanism
#45 opened by dgarnitz - 1
Implement Metrics Tracking / Telemetry
#87 opened by dgarnitz - 0
Add Task to Github Actions that Syncs the objects in src/models and client/models
#85 opened by dgarnitz - 3
Remove duplicate code
#80 opened by dgarnitz - 1
Ingest Zip Files via REST Api
#26 opened by dgarnitz - 1
Support larger file sizes
#36 opened by dgarnitz - 0
- 1
Job shows In Progress when Batch fails and throws SQL error when trying to update
#53 opened by dgarnitz - 5
Integration for MongoDB
#34 opened by prakul - 5
Add support for Chroma
#39 opened by dgarnitz - 5
Arguflow Use-Case
#60 opened by skeptrunedev - 12
Deploy Via Docker + HF = worker error
#61 opened by iguy0 - 2
Suggestion: Docs website
#48 opened by antondubek - 2
Fix Job Status Logic
#46 opened by dgarnitz - 3
Add support for word docs
#19 opened by dgarnitz - 2
Add file name to metadata schema
#56 opened by dgarnitz - 1
Add a testing client
#42 opened by dgarnitz - 2
Integrate with DeepLake
#17 opened by dgarnitz - 4
Upgrade Pinecone integration to use gRPC
#10 opened by dgarnitz - 1
Add documentation to README for new features
#40 opened by dgarnitz - 3
Add support for different chunking strategies
#12 opened by dgarnitz - 0
Multi-file ingestion from S3
#32 opened by dgarnitz - 1
Add s3 integration
#20 opened by dgarnitz - 0
Integrate with Milvus Cloud
#15 opened by dgarnitz - 5
Weaviate integration
#6 opened by philipvollet