phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add ChunkMetadata to Chunk (#2497)

Browse source 
# What does this PR do?
Adding `ChunkMetadata` so we can properly delete embeddings later.

More specifically, this PR refactors and extends the chunk metadata
handling in the vector database and introduces a distinction between
metadata used for model context and backend-only metadata required for
chunk management, storage, and retrieval. It also improves chunk ID
generation and propagation throughout the stack, enhances test coverage,
and adds new utility modules.

```python
class ChunkMetadata(BaseModel):
    """
    `ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional information about the chunk that
        will NOT be inserted into the context during inference, but is required for backend functionality.
        Use `metadata` in `Chunk` for metadata that will be used during inference.
    """
    document_id: str | None = None
    chunk_id: str | None = None
    source: str | None = None
    created_timestamp: int | None = None
    updated_timestamp: int | None = None
    chunk_window: str | None = None
    chunk_tokenizer: str | None = None
    chunk_embedding_model: str | None = None
    chunk_embedding_dimension: int | None = None
    content_token_count: int | None = None
    metadata_token_count: int | None = None
```
Eventually we can migrate the document_id out of the `metadata` field.
I've introduced the changes so that `ChunkMetadata` is backwards
compatible with `metadata`.

<!-- If resolving an issue, uncomment and update the line below -->
Closes https://github.com/meta-llama/llama-stack/issues/2501 

## Test Plan
Added unit tests

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Arceo 2025-06-25 13:55:23 -06:00 • committed by GitHub
parent fa0b0c13d4
commit 82f13fe83e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 490 additions and 218 deletions
Download patch file Download diff file Expand all files Collapse all files

21
llama_stack/providers/inline/tool_runtime/rag/memory.py
View file

@ -81,6 +81,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
chunks = []
for doc in documents:
content = await content_from_doc(doc)
# TODO: we should add enrichment here as URLs won't be added to the metadata by default
chunks.extend(
make_overlapped_chunks(
doc.document_id,
@ -157,8 +158,24 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
)
break
metadata_subset = {k: v for k, v in metadata.items() if k not in ["token_count", "metadata_token_count"]}
text_content = query_config.chunk_template.format(index=i + 1, chunk=chunk, metadata=metadata_subset)
# Add useful keys from chunk_metadata to metadata and remove some from metadata
chunk_metadata_keys_to_include_from_context = [
"chunk_id",
"document_id",
"source",
]
metadata_keys_to_exclude_from_context = [
"token_count",
"metadata_token_count",
]
metadata_for_context = {}
for k in chunk_metadata_keys_to_include_from_context:
metadata_for_context[k] = getattr(chunk.chunk_metadata, k)
for k in metadata:
if k not in metadata_keys_to_exclude_from_context:
metadata_for_context[k] = metadata[k]
text_content = query_config.chunk_template.format(index=i + 1, chunk=chunk, metadata=metadata_for_context)
picked.append(TextContentItem(text=text_content))
picked.append(TextContentItem(text="END of knowledge_search tool results.\n"))