Update app.py

app.py

@@ -1,111 +1,93 @@
-import streamlit as st
-import os
-import faiss
-import logging
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.llms import HuggingFacePipeline
-from langchain.chains import RetrievalQA
-from ingest import create_faiss_index
-
-# Set up logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-checkpoint = "LaMini-T5-738M"
-
-@st.cache_resource
-def load_llm():
-    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-    model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
-    pipe = pipeline(
-        'text2text-generation',
-        model=model,
-        tokenizer=tokenizer,
-        max_length=256,
-        do_sample=True,
-        temperature=0.3,
-        top_p=0.95
-    )
-    return HuggingFacePipeline(pipeline=pipe)
-
-def validate_index_file(index_path):
-    try:
-        with open(index_path, 'rb') as f:
-            data = f.read(100)
-        logger.info(f"Successfully read {len(data)} bytes from the index file")
-        return True
-    except Exception as e:
-        logger.error(f"Error validating index file: {e}")
-        return False
-
-def load_faiss_index():
-    index_path = "faiss_index/index.faiss"
-    if not os.path.exists(index_path):
-        st.warning("Index file not found. Creating a new one...")
-        create_faiss_index()
-
-    if not os.path.exists(index_path):
-        st.error("Failed to create the FAISS index. Please check the 'docs' directory and try again.")
-        raise RuntimeError("FAISS index creation failed.")
-
-    try:
-        index = faiss.read_index(index_path)
-        if index is None:
-            raise ValueError("Failed to read FAISS index.")
-        
-        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-        db = FAISS.load_local("faiss_index", embeddings)
-        if db.index is None or db.index_to_docstore_id is None:
-            raise ValueError("FAISS index or docstore_id mapping is None.")
-
-        return db.as_retriever()
-    except Exception as e:
-        st.error(f"Failed to load FAISS index: {e}")
-        logger.exception("Exception in load_faiss_index")
-        raise
-
-def process_answer(instruction):
-    try:
-        retriever = load_faiss_index()
-        llm = load_llm()
-        qa = RetrievalQA.from_chain_type(
-            llm=llm,
-            chain_type="stuff",
-            retriever=retriever,
-            return_source_documents=True
-        )
-        generated_text = qa.invoke(instruction)
-        answer = generated_text['result']
-        return answer, generated_text
-    except Exception as e:
-        st.error(f"An error occurred while processing the answer: {e}")
-        logger.exception("Exception in process_answer")
-        return "An error occurred while processing your request.", {}
-
-def main():
-    st.title("Search Your PDF 📚📝")
-    
-    with st.expander("About the App"):
-        st.markdown(
-            """
-            This is a Generative AI powered Question and Answering app that responds to questions about your PDF File.
-            """
-        )
-
-    question = st.text_area("Enter your Question")
-    
-    if st.button("Ask"):
-        st.info("Your Question: " + question)
-        st.info("Your Answer")
-        try:
-            answer, metadata = process_answer(question)
-            st.write(answer)
-            st.write(metadata)
-        except Exception as e:
-            st.error(f"An unexpected error occurred: {e}")
-            logger.exception("Unexpected error in main function")
-
-if __name__ == '__main__':
+import streamlit as st
+import os
+import logging
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_community.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from ingest import create_chroma_db
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+checkpoint = "LaMini-T5-738M"
+
+@st.cache_resource
+def load_llm():
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
+    pipe = pipeline(
+        'text2text-generation',
+        model=model,
+        tokenizer=tokenizer,
+        max_length=256,
+        do_sample=True,
+        temperature=0.3,
+        top_p=0.95
+    )
+    return HuggingFacePipeline(pipeline=pipe)
+
+def load_chroma_db():
+    chroma_dir = "chroma_db"
+    if not os.path.exists(chroma_dir):
+        st.warning("Chroma database not found. Creating a new one...")
+        create_chroma_db()
+
+    if not os.path.exists(chroma_dir):
+        st.error("Failed to create the Chroma database. Please check the 'docs' directory and try again.")
+        raise RuntimeError("Chroma database creation failed.")
+
+    try:
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        db = Chroma.load_local(chroma_dir, embeddings)
+        return db.as_retriever()
+    except Exception as e:
+        st.error(f"Failed to load Chroma database: {e}")
+        logger.exception("Exception in load_chroma_db")
+        raise
+
+def process_answer(instruction):
+    try:
+        retriever = load_chroma_db()
+        llm = load_llm()
+        qa = RetrievalQA.from_chain_type(
+            llm=llm,
+            chain_type="stuff",
+            retriever=retriever,
+            return_source_documents=True
+        )
+        generated_text = qa.invoke(instruction)
+        answer = generated_text['result']
+        return answer, generated_text
+    except Exception as e:
+        st.error(f"An error occurred while processing the answer: {e}")
+        logger.exception("Exception in process_answer")
+        return "An error occurred while processing your request.", {}
+
+def main():
+    st.title("Search Your PDF 📚📝")
+    
+    with st.expander("About the App"):
+        st.markdown(
+            """
+            This is a Generative AI powered Question and Answering app that responds to questions about your PDF File.
+            """
+        )
+
+    question = st.text_area("Enter your Question")
+    
+    if st.button("Ask"):
+        st.info("Your Question: " + question)
+        st.info("Your Answer")
+        try:
+            answer, metadata = process_answer(question)
+            st.write(answer)
+            st.write(metadata)
+        except Exception as e:
+            st.error(f"An unexpected error occurred: {e}")
+            logger.exception("Unexpected error in main function")
+
+if __name__ == '__main__':
     main()