feat: Bump langchain dependencies to 1.0.x

- Update langchain from 0.1.16 to ^1.0.2
- Update langchain_core from 0.1.42 to ^1.0.0
- Add langchain_community ^0.4 as explicit dependency
- Update imports to use new langchain package structure:
  - langchain_community.embeddings for embedding classes
  - langchain_text_splitters for text splitting
  - langchain_core.utils.strings for utility functions
- Fix CohereEmbeddings initialization to include required user_agent parameter
- All fast tests passing (3800 passed)

Co-Authored-By: AJ Steers <[email protected]>

Author: devin-ai-integration[bot]

airbyte_cdk/destinations/vector_db_based/document_processor.py

@@ -8,9 +8,9 @@
 from typing import Any, Dict, List, Mapping, Optional, Tuple
 
 import dpath
-from langchain.text_splitter import Language, RecursiveCharacterTextSplitter
-from langchain.utils import stringify_dict
+from langchain_text_splitters import Language, RecursiveCharacterTextSplitter
 from langchain_core.documents.base import Document
+from langchain_core.utils.strings import stringify_dict
 
 from airbyte_cdk.destinations.vector_db_based.config import (
     ProcessingConfigModel,

airbyte_cdk/destinations/vector_db_based/embedder.py

@@ -7,10 +7,7 @@
 from dataclasses import dataclass
 from typing import List, Optional, Union, cast
 
-from langchain.embeddings.cohere import CohereEmbeddings
-from langchain.embeddings.fake import FakeEmbeddings
-from langchain.embeddings.localai import LocalAIEmbeddings
-from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain_community.embeddings import CohereEmbeddings, FakeEmbeddings, LocalAIEmbeddings, OpenAIEmbeddings
 
 from airbyte_cdk.destinations.vector_db_based.config import (
     AzureOpenAIEmbeddingConfigModel,
@@ -140,7 +137,7 @@ def __init__(self, config: CohereEmbeddingConfigModel):
         super().__init__()
         # Client is set internally
         self.embeddings = CohereEmbeddings(
-            cohere_api_key=config.cohere_key, model="embed-english-light-v2.0"
+            cohere_api_key=config.cohere_key, model="embed-english-light-v2.0", user_agent="airbyte-cdk"
         )  # type: ignore
 
     def check(self) -> Optional[str]: