Update app.py

app.py

@@ -1,39 +1,39 @@
+import os 
 import gradio as gr
-import tiktoken
+import pandas as pd
 
-import os
+from langchain_openai import OpenAIEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import Chroma
-from langchain.document_loaders import TextLoader
-from langchain import PromptTemplate
+#from langchain.vectorstores import Chroma
+from langchain_community.vectorstores import Chroma
+from langchain_community.document_loaders import TextLoader
+from langchain_community.chat_models import ChatOpenAI
+# from langchain import PromptTemplate
+from langchain_core.prompts import PromptTemplate
 from langchain.chains import LLMChain
-from langchain.chains.qa_with_sources import load_qa_with_sources_chain
-from langchain.llms import OpenAI
-from langchain.vectorstores import FAISS
-from langchain_openai import OpenAIEmbeddings
-from langchain_openai import ChatOpenAI
+from langchain_community.llms import OpenAI
+#from langchain.vectorstores import FAISS
+from langchain_community.vectorstores.faiss import FAISS
 
-# Load the FAISS index from the .pkl file
-openai_api_key = os.getenv("OPENAI_API_KEY")
-if not openai_api_key:
-    raise ValueError("OPENAI_API_KEY environment variable is not set.")
+# embeddings = OpenAIEmbeddings()
 
-embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
-#with open("index.pkl", "rb") as f:
- #   db = faiss.read_index(f.read())
-#with open("index.pkl", "rb") as f:
-    #db = faiss.deserialize_index(f.read())
+openai_api_key = os.getenv("OPENAI_API_KEY")
+try:
+    embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
+except ValidationError as e:
+    print(f"Error: {e}")
 
-db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
 
+#------------------------------------------------------------------------------
+db=FAISS.load_local("faiss_index", embeddings,allow_dangerous_deserialization=True)
+#-----------------------------------------------------------------------------
 def get_response_from_query(db, query, k=3):
 
     docs = db.similarity_search(query, k=k)
 
     docs_page_content = " ".join([d.page_content for d in docs])
 
-    # llm = BardLLM()
     llm = ChatOpenAI(model_name="gpt-3.5-turbo-16k",temperature=0)
 
     prompt = PromptTemplate(
@@ -48,6 +48,9 @@ def get_response_from_query(db, query, k=3):
     )
 
     chain = LLMChain(llm=llm, prompt=prompt)
+    # chain = RetrievalQAWithSourcesChain.from_chain_type(llm=llm, prompt=prompt,
+    #                                                     chain_type="stuff", retriever=db.as_retriever(), return_source_documents=True)
+
     response = chain.run(question=query, docs=docs_page_content,return_source_documents=True)
     r_text = str(response)
 
@@ -70,24 +73,14 @@ def get_response_from_query(db, query, k=3):
 
     return response,docs,evals
 
-
-
 def greet(query):
 
     answer,sources,evals = get_response_from_query(db,query,2)
     return answer,sources,evals
-examples = [
-    ["How to be happy"],
-    ["Climate Change Challenges in Europe"],
-    ["Philosophy in the world of Minimalism"],
-    ["Hate Speech  vs Freedom of Speech"],
-    ["Articles by Noam Chomsky on US Politics"],
-    ["The importance of values and reflection"]
-    ]
+
 demo = gr.Interface(fn=greet, title="cicero-semantic-search", inputs="text",
                     outputs=[gr.components.Textbox(lines=3, label="Response"),
                              gr.components.Textbox(lines=3, label="Source"),
-                             gr.components.Textbox(lines=3, label="Evaluation")],
-                   examples=examples)
+                             gr.components.Textbox(lines=3, label="Evaluation")])
 
-demo.launch(share=True)
+demo.launch(share=True, debug=True)