phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-02 04:28:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Enable ingestion of custom embeddings

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-05-29 20:58:41 -04:00 • committed by Francisco Arceo
parent 2603f10f95
commit 73456878e5
8 changed files with 224 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

25
docs/source/building_applications/rag.md
View file

@ -57,6 +57,31 @@ chunks = [
]
client.vector_io.insert(vector_db_id=vector_db_id, chunks=chunks)
```
#### Using Precomputed Embeddings
If you decide to precompute embeddings for your documents, you can insert them directly into the vector database by
including the embedding vectors in the chunk data. This is useful if you have a separate embedding service or if you
want to customize the ingestion process.
```python
chunks_with_embeddings = [
{
"content": "First chunk of text",
"mime_type": "text/plain",
"embedding": [0.1, 0.2, 0.3, ...], # Your precomputed embedding vector
"metadata": {"document_id": "doc1", "section": "introduction"},
},
{
"content": "Second chunk of text",
"mime_type": "text/plain",
"embedding": [0.2, 0.3, 0.4, ...], # Your precomputed embedding vector
"metadata": {"document_id": "doc1", "section": "methodology"},
},
]
client.vector_io.insert(vector_db_id=vector_db_id, chunks=chunks_with_embeddings)
```
When providing precomputed embeddings, ensure the embedding dimension matches the embedding_dimension specified when
registering the vector database.
### Retrieval
You can query the vector database to retrieve documents based on their embeddings.
```python