Update app.py

app.py

@@ -1,30 +1,23 @@
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.text_splitter import NLTKTextSplitter
 from langchain.vectorstores import Chroma
-from langchain.docstore.document import Document
-from langchain.prompts import PromptTemplate
-from langchain.indexes.vectorstore import VectorstoreIndexCreator
 from langchain.chains.question_answering import load_qa_chain
 from langchain.llms import OpenAI
-import nltk
 import os
 
-nltk.download("punkt")
-
 with open("guide1.txt") as f:
     hitchhikersguide = f.read()
 
-text_splitter = NLTKTextSplitter()
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0, separator = "\n")
 texts = text_splitter.split_text(hitchhikersguide)
 
+embeddings = OpenAIEmbeddings()
+
+docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))]).as_retriever()
+
+chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
 
-def make_inference(query, openai_key=""):
-    os.environ["OPENAI_API_KEY"] = openai_key
-    embeddings = OpenAIEmbeddings()
-    docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))]).as_retriever()
-    chain = load_qa_chain(OpenAI(temperature=0), chain_type="refine")
-    docs = docsearch.get_relevant_documents(query)
-    return chain({"input_documents": docs, "question": query}, return_only_outputs=True)
+def make_inference(query):
+    chain.run(input_documents=docs, question=query)
 
 if __name__ == "__main__":
     # make a gradio interface
@@ -34,7 +27,6 @@ if __name__ == "__main__":
         make_inference,
         [
             gr.inputs.Textbox(lines=2, label="Query"),
-            gr.inputs.Textbox(lines=2, label="OpenAI Key"),
         ],
         gr.outputs.Textbox(label="Response"),
         title="🗣️TalkToMyDoc📄",