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

[fix] index_not_found_exception

Browse Source
This commit is contained in:
Mark
2026-05-06 18:34:07 +08:00
parent 70c6d161c8
commit ad2e885f72
1 changed files with 23 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
api/app/core/rag/vdb/elasticsearch/elasticsearch_vector.py
View File

@@ -5,7 +5,7 @@ from typing import Any
from urllib.parse import urlparse from urllib.parse import urlparse
import requests import requests
from elasticsearch import Elasticsearch, helpers from elasticsearch import Elasticsearch, helpers, NotFoundError
from elasticsearch.helpers import BulkIndexError from elasticsearch.helpers import BulkIndexError
from packaging.version import parse as parse_version from packaging.version import parse as parse_version
# langchain-community # langchain-community
@@ -225,6 +225,8 @@ class ElasticSearchVector(BaseVector):
List of DocumentChunk objects that match the query. List of DocumentChunk objects that match the query.
""" """
indices = kwargs.get("indices", self._collection_name) # Default single index, multiple indexes are also supported, such as "index1, index2, index3" indices = kwargs.get("indices", self._collection_name) # Default single index, multiple indexes are also supported, such as "index1, index2, index3"
if not self._client.indices.exists(index=indices):
return 0, []
# Calculate the start position for the current page # Calculate the start position for the current page
from_ = pagesize * (page-1) from_ = pagesize * (page-1)
@@ -259,12 +261,15 @@ class ElasticSearchVector(BaseVector):
}) })
# For simplicity, we use from/size here which has a limit (usually up to 10,000). # For simplicity, we use from/size here which has a limit (usually up to 10,000).
result = self._client.search( try:
index=indices, result = self._client.search(
from_=from_, # Only use from_ for the first page (simplified) index=indices,
size=pagesize, from_=from_, # Only use from_ for the first page (simplified)
body=query_str, size=pagesize,
) body=query_str,
)
except NotFoundError:
return 0, []
if "errors" in result: if "errors" in result:
raise ValueError(f"Error during query: {result['errors']}") raise ValueError(f"Error during query: {result['errors']}")
@@ -309,13 +314,18 @@ class ElasticSearchVector(BaseVector):
List of DocumentChunk objects that match the query. List of DocumentChunk objects that match the query.
""" """
indices = kwargs.get("indices", self._collection_name) # Default single index, multi-index available，etc "index1,index2,index3" indices = kwargs.get("indices", self._collection_name) # Default single index, multi-index available，etc "index1,index2,index3"
if not self._client.indices.exists(index=indices):
return 0, []
query_str = {"query": {"term": {f"{Field.DOC_ID.value}": doc_id}}} query_str = {"query": {"term": {f"{Field.DOC_ID.value}": doc_id}}}
result = self._client.search( try:
index=indices, result = self._client.search(
from_=0, # Only use from_ for the first page (simplified) index=indices,
size=1, from_=0, # Only use from_ for the first page (simplified)
body=query_str, size=1,
) body=query_str,
)
except NotFoundError:
return 0, []
# print(result) # print(result)
if "errors" in result: if "errors" in result:
raise ValueError(f"Error during query: {result['errors']}") raise ValueError(f"Error during query: {result['errors']}")