github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-11 13:55:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make so explicit class constructor is called in ElasticVectorSearch from_texts (#6199)

Browse Source 
Fixes #6198 

ElasticKnnSearch.from_texts is actually ElasticVectorSearch.from_texts
and throws because it calls ElasticKnnSearch constructor with the wrong
arguments.

Now ElasticKnnSearch has its own from_texts, which constructs a proper
ElasticKnnSearch.

---------

Co-authored-by: Charles Parker <charlesparker@FiltaMacbook.local>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Charles P 2023-07-13 16:55:20 -07:00 committed by GitHub
parent 854f3fe9b1
commit 574698a5fb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 42 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
langchain/vectorstores/elastic_vector_search.py
View File

@ -17,7 +17,7 @@ from typing import (
from langchain.docstore.document import Document from langchain.docstore.document import Document
from langchain.embeddings.base import Embeddings from langchain.embeddings.base import Embeddings
from langchain.utils import get_from_env from langchain.utils import get_from_dict_or_env
from langchain.vectorstores.base import VectorStore from langchain.vectorstores.base import VectorStore
if TYPE_CHECKING: if TYPE_CHECKING:
@ -262,7 +262,6 @@ class ElasticVectorSearch(VectorStore, ABC):
embedding: Embeddings, embedding: Embeddings,
metadatas: Optional[List[dict]] = None, metadatas: Optional[List[dict]] = None,
ids: Optional[List[str]] = None, ids: Optional[List[str]] = None,
elasticsearch_url: Optional[str] = None,
index_name: Optional[str] = None, index_name: Optional[str] = None,
refresh_indices: bool = True, refresh_indices: bool = True,
**kwargs: Any, **kwargs: Any,
@ -288,8 +287,8 @@ class ElasticVectorSearch(VectorStore, ABC):
elasticsearch_url="http://localhost:9200" elasticsearch_url="http://localhost:9200"
) )
""" """
elasticsearch_url = elasticsearch_url or get_from_env( elasticsearch_url = get_from_dict_or_env(
"elasticsearch_url", "ELASTICSEARCH_URL" kwargs, "elasticsearch_url", "ELASTICSEARCH_URL"
) )
index_name = index_name or uuid.uuid4().hex index_name = index_name or uuid.uuid4().hex
vectorsearch = cls(elasticsearch_url, index_name, embedding, **kwargs) vectorsearch = cls(elasticsearch_url, index_name, embedding, **kwargs)
@ -368,7 +367,6 @@ class ElasticKnnSearch(ElasticVectorSearch):
es_password: The password for the Elasticsearch instance. Required if es_password: The password for the Elasticsearch instance. Required if
creating a new connection. creating a new connection.
""" """
try: try:
import elasticsearch import elasticsearch
except ImportError: except ImportError:
@ -398,6 +396,45 @@ class ElasticKnnSearch(ElasticVectorSearch):
or valid credentials for creating a new connection.""" or valid credentials for creating a new connection."""
) )
@classmethod
def from_texts(
cls,
texts: List[str],
embedding: Embeddings,
metadatas: Optional[List[dict]] = None,
ids: Optional[List[str]] = None,
index_name: Optional[str] = None,
refresh_indices: bool = True,
es_connection: Optional["Elasticsearch"] = None,
es_cloud_id: Optional[str] = None,
es_user: Optional[str] = None,
es_password: Optional[str] = None,
**kwargs: Any,
) -> ElasticKnnSearch:
"""Construct ElasticKnnSearch wrapper from raw documents.
This is a user-friendly interface that:
1. Embeds documents.
2. Creates a new index for the embeddings in the Elasticsearch instance.
3. Adds the documents to the newly created Elasticsearch index.
This is intended to be a quick way to get started.
"""
index_name = index_name or uuid.uuid4().hex
vectorsearch = cls(
index_name,
embedding,
es_connection=es_connection,
es_cloud_id=es_cloud_id,
es_user=es_user,
es_password=es_password,
**kwargs,
)
vectorsearch.add_texts(
texts, metadatas=metadatas, refresh_indices=refresh_indices, ids=ids
)
return vectorsearch
@staticmethod @staticmethod
def _default_knn_mapping(dims: int) -> Dict: def _default_knn_mapping(dims: int) -> Dict:
"""Generates a default index mapping for kNN search.""" """Generates a default index mapping for kNN search."""