wow

.gitignore

@@ -0,0 +1,2 @@
+.env
+.gitattributes

app.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceInstructEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain.chains import ConversationalRetrievalChain
-from langchain.llms import HuggingFaceHub
+from langchain_community.llms import HuggingFaceHub
 from langchain.memory import ConversationBufferMemory
 
 def make_vectorstore(embeddings):
@@ -31,7 +31,7 @@ def get_conversation(vectorstore):
     memory = ConversationBufferMemory(memory_key="chat_history",return_messages=True,)
 
     conversation_chain = ConversationalRetrievalChain.from_chain_type(
-        # llm=HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}),
+        llm=HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}, huggingfacehub_api_token = st.secrets["hf_token"]),
         chain_type="stuff", 
         retriever=vectorstore.as_retriever(),
         memory=memory)
@@ -45,7 +45,7 @@ def get_response(conversation_chain, query):
 
 def main():
     st.title("BetterZila RAG Enabled LLM")
-    embeddings = HuggingFaceInstructEmbeddings(repo_id="google/t5-v1_1-xl")
+    embeddings = HuggingFaceInstructEmbeddings(model_name="google/t5-v1_1-xl", model_kwargs = {'device': 'cpu'})
     vectorstore = make_vectorstore(embeddings)
     conversation_chain = get_conversation(vectorstore)
     queries = ["Can you give me an example from history where the enemy was crushed totally from the book?", "What's the point of making myself less accessible?", "Can you tell me the story of Queen Elizabeth I from this 48 laws of power book?"]

secrets.toml

@@ -0,0 +1 @@
+hf_token="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"