fixed langchain embedding call for azure: langchain-ai/langchain#4575

config.py

@@ -165,6 +165,7 @@ async def dispatch(self, request, call_next):
 RAG_AZURE_OPENAI_ENDPOINT = get_env_variable(
     "RAG_AZURE_OPENAI_ENDPOINT", AZURE_OPENAI_ENDPOINT
 ).rstrip("/")
+RAG_AZURE_CHUNK_SIZE = int(get_env_variable("RAG_AZURE_CHUNK_SIZE", "1"))
 HF_TOKEN = get_env_variable("HF_TOKEN", "")
 OLLAMA_BASE_URL = get_env_variable("OLLAMA_BASE_URL", "http://ollama:11434")
 AWS_ACCESS_KEY_ID = get_env_variable("AWS_ACCESS_KEY_ID", "")
@@ -191,6 +192,7 @@ def init_embeddings(provider, model):
             api_key=RAG_AZURE_OPENAI_API_KEY,
             azure_endpoint=RAG_AZURE_OPENAI_ENDPOINT,
             api_version=RAG_AZURE_OPENAI_API_VERSION,
+            chunk_size=RAG_AZURE_CHUNK_SIZE
         )
     elif provider == EmbeddingsProvider.HUGGINGFACE:
         from langchain_huggingface import HuggingFaceEmbeddings