phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

review and update .mdx links

Browse source
This commit is contained in:
Akram Ben Aissi 2025-11-04 14:59:10 +01:00
parent 2f504a08ed
commit 25faaaaf37
2 changed files with 10 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

19
docs/docs/concepts/file_operations_vector_stores.md → docs/docs/concepts/file_operations_vector_stores.mdx
View file

@ -85,15 +85,17 @@ The following vector store providers support file operations:
- **FAISS**: Fast in-memory vector similarity search - **FAISS**: Fast in-memory vector similarity search
- **SQLite-vec**: Disk-based storage with hybrid search capabilities - **SQLite-vec**: Disk-based storage with hybrid search capabilities
- **Milvus**: High-performance vector database with advanced indexing
### Remote Providers (Hosted) ### Remote Providers (Hosted)
- **ChromaDB**: Vector database with metadata filtering - **ChromaDB**: Vector database with metadata filtering
- **Qdrant**: Vector similarity search with payload filtering
- **Weaviate**: Vector database with GraphQL interface - **Weaviate**: Vector database with GraphQL interface
- **Postgres (PGVector)**: Vector extensions for PostgreSQL - **Postgres (PGVector)**: Vector extensions for PostgreSQL
### Both Inline & Remote Providers
- **Milvus**: High-performance vector database with advanced indexing
- **Qdrant**: Vector similarity search with payload filtering
## File Processing Pipeline ## File Processing Pipeline
### 1. File Upload ### 1. File Upload
@ -172,11 +174,6 @@ You can customize chunking when attaching files:
```python ```python
from llama_stack.apis.vector_io import VectorStoreChunkingStrategy from llama_stack.apis.vector_io import VectorStoreChunkingStrategy
# Custom chunking strategy
chunking_strategy = VectorStoreChunkingStrategy(
type="custom", max_chunk_size_tokens=1000, chunk_overlap_tokens=200
)
# Attach file with custom chunking # Attach file with custom chunking
file_attach_response = await client.vector_stores.files.create( file_attach_response = await client.vector_stores.files.create(
vector_store_id=vector_store.id, vector_store_id=vector_store.id,
@ -333,7 +330,7 @@ results = await client.vector_stores.search(
### Hybrid Search ### Hybrid Search
[SQLite-vec](../providers/vector_io/inline_sqlite-vec.md), [pgvector](../providers/vector_io/remote_pgvector.md), and [Milvus](../providers/vector_io/inline_milvus.md) support combining vector and keyword search. [SQLite-vec](../providers/vector_io/inline_sqlite-vec.mdx), [pgvector](../providers/vector_io/remote_pgvector.mdx), and [Milvus](../providers/vector_io/inline_milvus.mdx) support combining vector and keyword search.
## Performance Considerations ## Performance Considerations
@ -418,6 +415,6 @@ async def analyze_document(vector_store_id, file_id):
## Next Steps ## Next Steps
- Explore the [Files API documentation](../apis/files.md) for detailed API reference - Explore the [Files API documentation](../../providers/files/files.mdx) for detailed API reference
- Check [Vector Store Providers](../providers/vector_io/index.md) for specific implementation details - Check [Vector Store Providers](../providers/vector_io/index.mdx) for specific implementation details
- Review [Getting Started](../getting_started/index.md) for quick setup instructions - Review [Getting Started](../getting_started/quickstart.mdx) for quick setup instructions

5
docs/docs/providers/files/openai_file_operations_support.md
View file

@ -2,7 +2,7 @@
## Overview ## Overview
This document provides a comprehensive overview of file operations and Vector Store API support across all available vector store providers in Llama Stack. As of release 0.2.14, the following providers support full file operations integration. This document provides a comprehensive overview of file operations and Vector Store API support across all available vector store providers in Llama Stack. As of release 0.2.24, the following providers support full file operations integration.
## Supported Providers ## Supported Providers
@ -76,7 +76,6 @@ All supported providers offer the following file operations capabilities:
- **Default**: 800 tokens with 400 token overlap - **Default**: 800 tokens with 400 token overlap
- **Custom**: Configurable chunk sizes and overlap - **Custom**: Configurable chunk sizes and overlap
- **Semantic**: Intelligent boundary detection
- **Static**: Fixed-size chunks with overlap - **Static**: Fixed-size chunks with overlap
## Provider-Specific Features ## Provider-Specific Features
@ -285,7 +284,7 @@ Planned improvements for file operations support:
## Support and Resources ## Support and Resources
- **Documentation**: [File Operations and Vector Store Integration](../concepts/file_operations_vector_stores.md) - **Documentation**: [File Operations and Vector Store Integration](../../concepts/file_operations_vector_stores.mdx)
- **API Reference**: [Files API](files_api.md) - **API Reference**: [Files API](files_api.md)
- **Provider Docs**: [Vector Store Providers](../vector_io/index.md) - **Provider Docs**: [Vector Store Providers](../vector_io/index.md)
- **Examples**: [Getting Started](../getting_started/index.md) - **Examples**: [Getting Started](../getting_started/index.md)