phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 14:38:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Enabling teste for Weaviate

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

chore: Actually enabling Chroma unit tests

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

fixed tests

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

fix integration test

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

remove changes from weavbiate

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-07-23 21:20:16 -04:00
parent cd8715d327
commit 2defebc835
3 changed files with 56 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

42
llama_stack/providers/remote/vector_io/chroma/chroma.py
View file

@ -57,12 +57,16 @@ class ChromaIndex(EmbeddingIndex):
self.collection = collection
self.kvstore = kvstore
async def initialize(self):
# Chroma does not require explicit initialization, this is just a helper for unit tests
pass
async def add_chunks(self, chunks: list[Chunk], embeddings: NDArray):
assert len(chunks) == len(embeddings), (
f"Chunk length {len(chunks)} does not match embedding length {len(embeddings)}"
)
ids = [f"{c.metadata['document_id']}:chunk-{i}" for i, c in enumerate(chunks)]
ids = [f"{c.metadata.get('document_id', '')}:{c.chunk_id}" for c in chunks]
await maybe_await(
self.collection.add(
documents=[chunk.model_dump_json() for chunk in chunks],
@ -137,9 +141,12 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
self.client = None
self.cache = {}
self.kvstore: KVStore | None = None
self.vector_db_store = None
async def initialize(self) -> None:
self.kvstore = await kvstore_impl(self.config.kvstore)
self.vector_db_store = self.kvstore
if isinstance(self.config, RemoteChromaVectorIOConfig):
log.info(f"Connecting to Chroma server at: {self.config.url}")
url = self.config.url.rstrip("/")
@ -172,6 +179,10 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
)
async def unregister_vector_db(self, vector_db_id: str) -> None:
if vector_db_id not in self.cache:
log.warning(f"Vector DB {vector_db_id} not found")
return
await self.cache[vector_db_id].index.delete()
del self.cache[vector_db_id]
@ -182,6 +193,8 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
ttl_seconds: int | None = None,
) -> None:
index = await self._get_and_cache_vector_db_index(vector_db_id)
if index is None:
raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
await index.insert_chunks(chunks)
@ -193,18 +206,27 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
) -> QueryChunksResponse:
index = await self._get_and_cache_vector_db_index(vector_db_id)
if index is None:
raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
return await index.query_chunks(query, params)
async def _get_and_cache_vector_db_index(self, vector_db_id: str) -> VectorDBWithIndex:
if vector_db_id in self.cache:
return self.cache[vector_db_id]
vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
if not vector_db:
raise ValueError(f"Vector DB {vector_db_id} not found in Llama Stack")
collection = await maybe_await(self.client.get_collection(vector_db_id))
if not collection:
raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
index = VectorDBWithIndex(vector_db, ChromaIndex(self.client, collection), self.inference_api)
self.cache[vector_db_id] = index
return index
try:
collection = await maybe_await(self.client.get_collection(vector_db_id))
if not collection:
raise ValueError(f"Vector DB {vector_db_id} not found in Chroma")
vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
if not vector_db:
raise ValueError(f"Vector DB {vector_db_id} not found in Llama Stack")
index = VectorDBWithIndex(vector_db, ChromaIndex(self.client, collection), self.inference_api)
self.cache[vector_db_id] = index
return index
except Exception as exc:
raise ValueError(f"Vector DB {vector_db_id} not found in Chroma") from exc