admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

remove .value (#26633)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Asuka Minato
2025-10-11 10:08:29 +09:00
committed by GitHub
parent bb6a331490
commit 1bd621f819
138 changed files with 613 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
api/core/rag/datasource/vdb/elasticsearch/elasticsearch_ja_vector.py
View File

@@ -57,18 +57,18 @@ class ElasticSearchJaVector(ElasticSearchVector):
}
mappings = {
"properties": {
Field.CONTENT_KEY.value: {
Field.CONTENT_KEY: {
"type": "text",
"analyzer": "ja_analyzer",
"search_analyzer": "ja_analyzer",
},
Field.VECTOR.value: { # Make sure the dimension is correct here
Field.VECTOR: { # Make sure the dimension is correct here
"type": "dense_vector",
"dims": dim,
"index": True,
"similarity": "cosine",
},
Field.METADATA_KEY.value: {
Field.METADATA_KEY: {
"type": "object",
"properties": {
"doc_id": {"type": "keyword"} # Map doc_id to keyword type

30
api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py
View File

@@ -163,9 +163,9 @@ class ElasticSearchVector(BaseVector):
index=self._collection_name,
id=uuids[i],
document={
Field.CONTENT_KEY.value: documents[i].page_content,
Field.VECTOR.value: embeddings[i] or None,
Field.METADATA_KEY.value: documents[i].metadata or {},
Field.CONTENT_KEY: documents[i].page_content,
Field.VECTOR: embeddings[i] or None,
Field.METADATA_KEY: documents[i].metadata or {},
},
)
self._client.indices.refresh(index=self._collection_name)
@@ -193,7 +193,7 @@ class ElasticSearchVector(BaseVector):
def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
top_k = kwargs.get("top_k", 4)
num_candidates = math.ceil(top_k * 1.5)
knn = {"field": Field.VECTOR.value, "query_vector": query_vector, "k": top_k, "num_candidates": num_candidates}
knn = {"field": Field.VECTOR, "query_vector": query_vector, "k": top_k, "num_candidates": num_candidates}
document_ids_filter = kwargs.get("document_ids_filter")
if document_ids_filter:
knn["filter"] = {"terms": {"metadata.document_id": document_ids_filter}}
@@ -205,9 +205,9 @@ class ElasticSearchVector(BaseVector):
docs_and_scores.append(
(
Document(
page_content=hit["_source"][Field.CONTENT_KEY.value],
vector=hit["_source"][Field.VECTOR.value],
metadata=hit["_source"][Field.METADATA_KEY.value],
page_content=hit["_source"][Field.CONTENT_KEY],
vector=hit["_source"][Field.VECTOR],
metadata=hit["_source"][Field.METADATA_KEY],
),
hit["_score"],
)
@@ -224,13 +224,13 @@ class ElasticSearchVector(BaseVector):
return docs
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
query_str: dict[str, Any] = {"match": {Field.CONTENT_KEY.value: query}}
query_str: dict[str, Any] = {"match": {Field.CONTENT_KEY: query}}
document_ids_filter = kwargs.get("document_ids_filter")
if document_ids_filter:
query_str = {
"bool": {
"must": {"match": {Field.CONTENT_KEY.value: query}},
"must": {"match": {Field.CONTENT_KEY: query}},
"filter": {"terms": {"metadata.document_id": document_ids_filter}},
}
}
@@ -240,9 +240,9 @@ class ElasticSearchVector(BaseVector):
for hit in results["hits"]["hits"]:
docs.append(
Document(
page_content=hit["_source"][Field.CONTENT_KEY.value],
vector=hit["_source"][Field.VECTOR.value],
metadata=hit["_source"][Field.METADATA_KEY.value],
page_content=hit["_source"][Field.CONTENT_KEY],
vector=hit["_source"][Field.VECTOR],
metadata=hit["_source"][Field.METADATA_KEY],
)
)
@@ -270,14 +270,14 @@ class ElasticSearchVector(BaseVector):
dim = len(embeddings[0])
mappings = {
"properties": {
Field.CONTENT_KEY.value: {"type": "text"},
Field.VECTOR.value: { # Make sure the dimension is correct here
Field.CONTENT_KEY: {"type": "text"},
Field.VECTOR: { # Make sure the dimension is correct here
"type": "dense_vector",
"dims": dim,
"index": True,
"similarity": "cosine",
},
Field.METADATA_KEY.value: {
Field.METADATA_KEY: {
"type": "object",
"properties": {
"doc_id": {"type": "keyword"}, # Map doc_id to keyword type