Merge pull request #2 from almutareb/1_resolve_LC_warnings

app/api/v1/agents/hf_mixtral_agent.py

@@ -1,5 +1,5 @@
 # HF libraries
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import HuggingFaceEndpoint
 from langchain.agents import AgentExecutor
 from langchain.agents.format_scratchpad import format_log_to_str
 from langchain.agents.output_parsers import ReActJsonSingleInputOutputParser
@@ -21,7 +21,7 @@ from app.templates.react_json_with_memory import template_system
 from app.utils import logger
 from app.utils import utils
 from langchain.globals import set_llm_cache
-from langchain.cache import SQLiteCache
+from langchain_community.cache import SQLiteCache
 from app.utils.callback import (
     CustomAsyncCallbackHandler,
     CustomFinalStreamingStdOutCallbackHandler,

app/structured_tools/structured_tools.py

@@ -4,7 +4,7 @@ from langchain_community.retrievers import ArxivRetriever
 from langchain_community.tools import WikipediaQueryRun
 from langchain_community.utilities import WikipediaAPIWrapper
 #from langchain.tools import Tool
-from langchain_community.utilities import GoogleSearchAPIWrapper
+from langchain_google_community import GoogleSearchAPIWrapper
 from langchain_community.embeddings.sentence_transformer import (
     SentenceTransformerEmbeddings,
 )
@@ -52,11 +52,11 @@ def memory_search(query:str) -> str:
     collection_name = settings.CONVERSATION_COLLECTION_NAME
     #store using envar
     
-    # embedding_function = SentenceTransformerEmbeddings(
-    #     model_name=settings.EMBEDDING_MODEL
-    #     #model_name=os.getenv("EMBEDDING_MODEL"),
-    #     )
-    embedding_function = GPT4AllEmbeddings()
+    embedding_function = SentenceTransformerEmbeddings(
+         model_name=settings.EMBEDDING_MODEL
+         #model_name=os.getenv("EMBEDDING_MODEL"),
+         )
+    #embedding_function = GPT4AllEmbeddings()
     
     vector_db = Chroma(
     client=client, # client for Chroma
@@ -80,11 +80,11 @@ def knowledgeBase_search(query:str) -> str:
     collection_name="ArxivPapers"
     #store using envar
     
-    # embedding_function = SentenceTransformerEmbeddings(
-    #     #model_name=os.getenv("EMBEDDING_MODEL"),
-    #     model_name=settings.EMBEDDING_MODEL
-    #     )
-    embedding_function = GPT4AllEmbeddings()
+    embedding_function = SentenceTransformerEmbeddings(
+         #model_name=os.getenv("EMBEDDING_MODEL"),
+         model_name=settings.EMBEDDING_MODEL
+         )
+    #embedding_function = GPT4AllEmbeddings()
     
     vector_db = Chroma(
         client=client, # client for Chroma

requirements.txt

@@ -1,5 +1,7 @@
 langchain-community
 langchain
+langchain-google-community
+langchain-huggingface
 google-search-results
 langchainhub
 arxiv