adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge #41 into develop from feature/20251219_myh

Browse Source 
feat(workflow): implement a workflow node for knowledge base retrieval

* feature/20251219_myh: (3 commits)
  feat(workflow): support multi-variable assignment in assigner node
  feat(workflow): implement a workflow node for knowledge base retrieval
  fix(template): remove default initial model in templates

Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/41
This commit is contained in:
朱文辉
2025-12-24 12:21:14 +08:00
parent ea9e5a689a b99671e04a
commit 0c3486248f
13 changed files with 243 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
api/app/core/rag/vdb/elasticsearch/elasticsearch_vector.py
View File

@@ -740,8 +740,9 @@ class ElasticSearchVector(BaseVector):
self._client.indices.create(index=self._collection_name, body=index_mapping)
class ElasticSearchVectorFactory(ABC):
def init_vector(self, knowledge: Knowledge) -> ElasticSearchVector:
class ElasticSearchVectorFactory:
@staticmethod
def init_vector(knowledge: Knowledge) -> ElasticSearchVector:
collection_name = f"Vector_index_{knowledge.id}_Node"
# Use regular Elasticsearch with config values
@@ -763,17 +764,17 @@ class ElasticSearchVectorFactory(ABC):
}
)
if knowledge.embedding and knowledge.reranker:
return ElasticSearchVector(
index_name=collection_name,
config=ElasticSearchConfig(**config_dict),
embedding_config=knowledge.embedding.api_keys[0],
reranker_config=knowledge.reranker.api_keys[0]
)
else:
if knowledge.embedding is None:
raise ValueError(f"embedding_id config error: {str(knowledge.embedding_id)}")
if knowledge.reranker is None:
raise ValueError(f"reranker_id config error: {str(knowledge.reranker_id)}")
if knowledge.embedding is None:
raise ValueError(f"embedding_id config error: {str(knowledge.embedding_id)}")
if knowledge.reranker is None:
raise ValueError(f"reranker_id config error: {str(knowledge.reranker_id)}")
return ElasticSearchVector(
index_name=collection_name,
config=ElasticSearchConfig(**config_dict),
embedding_config=knowledge.embedding.api_keys[0],
reranker_config=knowledge.reranker.api_keys[0]
)