Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Lindorm vdb bug-fix #11790

Merged
merged 9 commits into from
Dec 18, 2024
+11 −6
Merged

Lindorm vdb bug-fix #11790

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
39cdfcf
fix the wrong LINDORM_PASSWORD variable name in docker-compose.yaml
Nov 25, 2024
4a98a13
Merge branch 'langgenius:main' into lindorm-vdb
AlwaysBluer Dec 11, 2024
fc5fe4d
lindorm vdb add ugc feature
Dec 11, 2024
c5543e4
reformat and lint checks
Dec 12, 2024
299518f
Merge branch 'langgenius:main' into lindorm-vdb
AlwaysBluer Dec 13, 2024
47695de
fix lindorm vdb bugs
Dec 18, 2024
179dfe9
Merge branch 'lindorm-vdb' of github.com:AlwaysBluer/dify into lindor…
Dec 18, 2024
7f3b8e0
Merge branch 'langgenius:main' into lindorm-vdb
AlwaysBluer Dec 18, 2024
6ae50b5
run reformat
Dec 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 11 additions & 6 deletions api/core/rag/datasource/vdb/lindorm/lindorm_vector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,10 +49,10 @@ def to_opensearch_params(self) -> dict[str, Any]:


class LindormVectorStore(BaseVector):
def __init__(self, collection_name: str, config: LindormVectorStoreConfig, **kwargs):
def __init__(self, collection_name: str, config: LindormVectorStoreConfig, using_ugc: bool, **kwargs):
self._routing = None
self._routing_field = None
if config.using_ugc:
if using_ugc:
routing_value: str = kwargs.get("routing_value")
if routing_value is None:
raise ValueError("UGC index should init vector with valid 'routing_value' parameter value")
Expand All @@ -64,7 +64,7 @@ def __init__(self, collection_name: str, config: LindormVectorStoreConfig, **kwa
super().__init__(collection_name.lower())
self._client_config = config
self._client = OpenSearch(**config.to_opensearch_params())
self._using_ugc = config.using_ugc
self._using_ugc = using_ugc
self.kwargs = kwargs

def get_type(self) -> str:
Expand Down Expand Up @@ -467,12 +467,16 @@ def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings
using_ugc = dify_config.USING_UGC_INDEX
routing_value = None
if dataset.index_struct:
if using_ugc:
# if an existed record's index_struct_dict doesn't contain using_ugc field,
# it actually stores in the normal index format
stored_in_ugc = dataset.index_struct_dict.get("using_ugc", False)
using_ugc = stored_in_ugc
if stored_in_ugc:
dimension = dataset.index_struct_dict["dimension"]
index_type = dataset.index_struct_dict["index_type"]
distance_type = dataset.index_struct_dict["distance_type"]
index_name = f"{UGC_INDEX_PREFIX}_{dimension}_{index_type}_{distance_type}"
routing_value = dataset.index_struct_dict["vector_store"]["class_prefix"]
index_name = f"{UGC_INDEX_PREFIX}_{dimension}_{index_type}_{distance_type}"
else:
index_name = dataset.index_struct_dict["vector_store"]["class_prefix"]
else:
Expand All @@ -487,11 +491,12 @@ def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings
"index_type": index_type,
"dimension": dimension,
"distance_type": distance_type,
"using_ugc": using_ugc,
}
dataset.index_struct = json.dumps(index_struct_dict)
if using_ugc:
index_name = f"{UGC_INDEX_PREFIX}_{dimension}_{index_type}_{distance_type}"
routing_value = class_prefix
else:
index_name = class_prefix
return LindormVectorStore(index_name, lindorm_config, routing_value=routing_value)
return LindormVectorStore(index_name, lindorm_config, routing_value=routing_value, using_ugc=using_ugc)
Loading