Fix Deprecation warnings in logs service logs

comps/dataprep/src/integrations/elasticsearch.py

@@ -12,6 +12,7 @@
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_core.documents import Document
 from langchain_elasticsearch import ElasticsearchStore
+from langchain_huggingface import HuggingFaceEmbeddings
 
 from comps import CustomLogger, DocPath, OpeaComponent, OpeaComponentRegistry, ServiceType
 from comps.dataprep.src.utils import (
@@ -78,7 +79,7 @@ def create_index(self) -> None:
         if not self.es_client.indices.exists(index=INDEX_NAME):
             self.es_client.indices.create(index=INDEX_NAME)
 
-    def get_embedder(self) -> Union[HuggingFaceInferenceAPIEmbeddings, HuggingFaceBgeEmbeddings]:
+    def get_embedder(self) -> Union[HuggingFaceInferenceAPIEmbeddings, HuggingFaceEmbeddings]:
         """Obtain required Embedder."""
         if TEI_EMBEDDING_ENDPOINT:
             if not HUGGINGFACEHUB_API_TOKEN:
@@ -99,10 +100,10 @@ def get_embedder(self) -> Union[HuggingFaceInferenceAPIEmbeddings, HuggingFaceBg
             )
             return embedder
         else:
-            return HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            return HuggingFaceEmbeddings(model_name=EMBED_MODEL)
 
     def get_elastic_store(
-        self, embedder: Union[HuggingFaceInferenceAPIEmbeddings, HuggingFaceBgeEmbeddings]
+        self, embedder: Union[HuggingFaceInferenceAPIEmbeddings, HuggingFaceEmbeddings]
     ) -> ElasticsearchStore:
         """Get Elasticsearch vector store."""
         return ElasticsearchStore(index_name=INDEX_NAME, embedding=embedder, es_connection=self.es_client)

comps/dataprep/src/integrations/milvus.py

@@ -12,6 +12,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings, OpenAIEmbeddings
 from langchain_core.documents import Document
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_milvus.vectorstores import Milvus
 from langchain_text_splitters import HTMLHeaderTextSplitter
 
@@ -213,7 +214,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ milvus embedding ] LOCAL_EMBEDDING_MODEL:{LOCAL_EMBEDDING_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=LOCAL_EMBEDDING_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=LOCAL_EMBEDDING_MODEL)
         return embeddings
 
     def check_health(self) -> bool:

comps/dataprep/src/integrations/opensearch.py

@@ -9,6 +9,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import OpenSearchVectorSearch
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_text_splitters import HTMLHeaderTextSplitter
 from opensearchpy import OpenSearch
 
@@ -99,7 +100,7 @@ def __init__(self, name: str, description: str, config: dict = None):
                 api_key=HUGGINGFACEHUB_API_TOKEN, model_name=model_id, api_url=TEI_EMBEDDING_ENDPOINT
             )
         else:
-            self.embeddings = HuggingFaceBgeEmbeddings(model_name=Config.EMBED_MODEL)
+            self.embeddings = HuggingFaceEmbeddings(model_name=Config.EMBED_MODEL)
 
         # OpenSearch client setup
         self.auth = ("admin", Config.OPENSEARCH_INITIAL_ADMIN_PASSWORD)

comps/dataprep/src/integrations/pgvect.py

@@ -12,6 +12,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import PGVector
+from langchain_huggingface import HuggingFaceEmbeddings
 
 from comps import CustomLogger, DocPath, OpeaComponent, OpeaComponentRegistry, ServiceType
 from comps.dataprep.src.utils import (
@@ -73,7 +74,7 @@ def __init__(self, name: str, description: str, config: dict = None):
             )
         else:
             # create embeddings using local embedding model
-            self.embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            self.embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
 
         # Perform health check
         health_status = self.check_health()

comps/dataprep/src/integrations/pipecone.py

@@ -9,6 +9,7 @@
 from fastapi import Body, File, Form, HTTPException, UploadFile
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_pinecone import PineconeVectorStore
 from langchain_text_splitters import HTMLHeaderTextSplitter
 from pinecone import Pinecone, ServerlessSpec
@@ -72,7 +73,7 @@ def __init__(self, name: str, description: str, config: dict = None):
             )
         else:
             # create embeddings using local embedding model
-            self.embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            self.embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         self.pc = Pinecone(api_key=PINECONE_API_KEY)
 
         # Perform health check

comps/dataprep/src/integrations/qdrant.py

@@ -9,6 +9,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import Qdrant
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_text_splitters import HTMLHeaderTextSplitter
 from qdrant_client import QdrantClient
 
@@ -70,7 +71,7 @@ def __init__(self, name: str, description: str, config: dict = None):
             )
         else:
             # create embeddings using local embedding model
-            self.embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            self.embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
 
         # Perform health check
         health_status = self.check_health()

comps/dataprep/src/integrations/redis.py

@@ -14,6 +14,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import Redis
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_text_splitters import HTMLHeaderTextSplitter
 from redis import asyncio as aioredis
 from redis.commands.search.field import TextField
@@ -326,7 +327,7 @@ async def _initialize_embedder(self):
             )
         else:
             # create embeddings using local embedding model
-            embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embedder
 
     async def check_health(self) -> bool:

comps/dataprep/src/integrations/utils/redis_finance_utils.py

@@ -9,7 +9,7 @@
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 from langchain_core.documents import Document
-from langchain_huggingface import HuggingFaceEndpointEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpointEmbeddings
 from langchain_redis import RedisConfig, RedisVectorStore
 from openai import OpenAI
 from tqdm import tqdm
@@ -47,7 +47,7 @@ def get_embedder():
         embedder = HuggingFaceEndpointEmbeddings(model=TEI_EMBEDDING_ENDPOINT)
     else:
         # create embeddings using local embedding model
-        embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+        embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
     return embedder
 
 

comps/dataprep/src/integrations/vdms.py

@@ -9,6 +9,7 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores.vdms import VDMS, VDMS_Client
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_text_splitters import HTMLHeaderTextSplitter
 
 from comps import CustomLogger, DocPath, OpeaComponent, OpeaComponentRegistry, ServiceType
@@ -83,7 +84,7 @@ def __init__(self, name: str, description: str, config: dict = None):
             )
         else:
             # create embeddings using local embedding model
-            self.embedder = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            self.embedder = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
 
         # Perform health check
         health_status = self.check_health()

comps/retrievers/src/integrations/elasticsearch.py

@@ -8,6 +8,7 @@
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_elasticsearch import ElasticsearchStore
+from langchain_huggingface import HuggingFaceEmbeddings
 
 from comps import CustomLogger, EmbedDoc, OpeaComponent, OpeaComponentRegistry, ServiceType
 
@@ -61,7 +62,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{EMBED_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embeddings
 
     def _initialize_client(self) -> Elasticsearch:

comps/retrievers/src/integrations/milvus.py

@@ -6,6 +6,7 @@
 
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_milvus.vectorstores import Milvus
 
 from comps import CustomLogger, EmbedDoc, OpeaComponent, OpeaComponentRegistry, ServiceType
@@ -64,7 +65,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{LOCAL_EMBEDDING_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=LOCAL_EMBEDDING_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=LOCAL_EMBEDDING_MODEL)
         return embeddings
 
     def _initialize_client(self) -> Milvus:

comps/retrievers/src/integrations/opensearch.py

@@ -9,6 +9,7 @@
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import OpenSearchVectorSearch
+from langchain_huggingface import HuggingFaceEmbeddings
 from pydantic import conlist
 
 from comps import CustomLogger, EmbedDoc, OpeaComponent, OpeaComponentRegistry, ServiceType
@@ -71,7 +72,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{EMBED_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embeddings
 
     def _initialize_client(self):

comps/retrievers/src/integrations/pgvector.py

@@ -7,6 +7,7 @@
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import PGVector
+from langchain_huggingface import HuggingFaceEmbeddings
 
 from comps import CustomLogger, EmbedDoc, OpeaComponent, OpeaComponentRegistry, ServiceType
 
@@ -60,7 +61,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{EMBED_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embeddings
 
     def _initialize_client(self) -> PGVector:

comps/retrievers/src/integrations/pinecone.py

@@ -7,6 +7,7 @@
 
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_pinecone import PineconeVectorStore
 from pinecone import Pinecone, ServerlessSpec
 
@@ -62,7 +63,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{EMBED_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embeddings
 
     def _initialize_client(self) -> Pinecone:

comps/retrievers/src/integrations/redis.py

@@ -48,9 +48,9 @@ def __init__(self, name: str, description: str, config: dict = None):
             self.embeddings = BridgeTowerEmbedding()
         else:
             # create embeddings using local embedding model
-            from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+            from langchain_community.embeddings import HuggingFaceEmbeddings
 
-            self.embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            self.embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         self.client = self._initialize_client()
         health_status = self.check_health()
         if not health_status:

comps/retrievers/src/integrations/vdms.py

@@ -7,6 +7,7 @@
 from fastapi import HTTPException
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores.vdms import VDMS, VDMS_Client
+from langchain_huggingface import HuggingFaceEmbeddings
 
 from comps import CustomLogger, EmbedDoc, OpeaComponent, OpeaComponentRegistry, ServiceType
 
@@ -73,7 +74,7 @@ def _initialize_embedder(self):
             # create embeddings using local embedding model
             if logflag:
                 logger.info(f"[ init embedder ] LOCAL_EMBEDDING_MODEL:{EMBED_MODEL}")
-            embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+            embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
         return embeddings
 
     def _initialize_vector_db(self) -> VDMS:

comps/third_parties/pathway/src/requirements.txt

@@ -1,5 +1,6 @@
 langchain
 langchain-community
+langchain-huggingface
 openai
 pathway[xpack-llm]
 sentence-transformers

comps/third_parties/pathway/src/vectorstore_pathway.py

@@ -8,6 +8,7 @@
 import pathway as pw
 from langchain import text_splitter
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings, HuggingFaceInferenceAPIEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 from pathway.xpacks.llm.parsers import ParseUnstructured
 from pathway.xpacks.llm.vector_store import VectorStoreServer
 
@@ -52,7 +53,7 @@
         )
     else:
         # create embeddings using local embedding model
-        embeddings = HuggingFaceBgeEmbeddings(model_name=EMBED_MODEL)
+        embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
 
     server = VectorStoreServer.from_langchain_components(
         *data_sources,

requirements.txt

@@ -7,6 +7,7 @@ httpx
 kubernetes
 langchain
 langchain-community
+langchain-huggingface
 opentelemetry-api
 opentelemetry-exporter-otlp
 opentelemetry-sdk