Upload 2 files

app.py

@@ -1,71 +1,70 @@
-import os
-import logging
-import streamlit as st
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import Chroma
-from langchain.chains import RetrievalQA
-from langchain_huggingface import HuggingFacePipeline
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
-
-# Configure logging
-logging.basicConfig(level=logging.DEBUG)
-
-def load_vector_store():
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vector_store = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)
-    return vector_store
-
-def load_llm():
-    checkpoint = "LaMini-T5-738M"
-    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 process_answer(question):
-    try:
-        vector_store = load_vector_store()
-        llm = load_llm()
-        qa = RetrievalQA.from_chain_type(
-            llm=llm,
-            chain_type="stuff",
-            retriever=vector_store.as_retriever(),
-            return_source_documents=True
-        )
-        result = qa.invoke(question)
-        answer = result['result']
-        return answer, result
-    except Exception as e:
-        logging.error(f"An error occurred while processing the answer: {e}")
-        st.error(f"An error occurred while processing the answer: {e}")
-        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}")
-
-if __name__ == '__main__':
-    main()
+import os
+import logging
+import streamlit as st
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQA
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+
+def load_vector_store():
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vector_store = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)
+    return vector_store
+
+def load_llm():
+    checkpoint = "LaMini-T5-738M"
+    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 pipe
+
+def process_answer(question):
+    try:
+        vector_store = load_vector_store()
+        llm = load_llm()
+        qa = RetrievalQA.from_chain_type(
+            llm=llm,
+            chain_type="stuff",
+            retriever=vector_store.as_retriever(),
+            return_source_documents=True
+        )
+        result = qa.invoke(question)
+        answer = result['result']
+        return answer, result
+    except Exception as e:
+        logging.error(f"An error occurred while processing the answer: {e}")
+        st.error(f"An error occurred while processing the answer: {e}")
+        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}")
+
+if __name__ == '__main__':
+    main()

ingest.py

@@ -1,64 +1,64 @@
-import os
-import logging
-from langchain.document_loaders import PDFMinerLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import Chroma
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-def create_vector_store():
-    documents = []
-    docs_dir = "docs"
-    if not os.path.exists(docs_dir):
-        logger.error(f"The directory '{docs_dir}' does not exist.")
-        return
-    
-    for root, dirs, files in os.walk(docs_dir):
-        for file in files:
-            if file.endswith(".pdf"):
-                file_path = os.path.join(root, file)
-                logger.info(f"Loading document: {file_path}")
-                try:
-                    loader = PDFMinerLoader(file_path)
-                    loaded_docs = loader.load()
-                    if loaded_docs:
-                        logger.info(f"Loaded {len(loaded_docs)} documents from {file_path}")
-                        documents.extend(loaded_docs)
-                    else:
-                        logger.warning(f"No documents loaded from {file_path}")
-                except Exception as e:
-                    logger.error(f"Error loading {file_path}: {e}")
-
-    if not documents:
-        logger.error("No documents were loaded. Check the 'docs' directory and file paths.")
-        return
-
-    logger.info(f"Loaded {len(documents)} documents.")
-
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    texts = text_splitter.split_documents(documents)
-    logger.info(f"Created {len(texts)} text chunks.")
-
-    if not texts:
-        logger.error("No text chunks created. Check the text splitting process.")
-        return
-
-    try:
-        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-        logger.info("Embeddings initialized successfully.")
-    except Exception as e:
-        logger.error(f"Failed to initialize embeddings: {e}")
-        return
-
-    try:
-        vector_store = Chroma.from_documents(texts, embeddings, persist_directory="./chroma_db")
-        vector_store.persist()
-        logger.info(f"Created Chroma vector store with {len(texts)} vectors.")
-    except Exception as e:
-        logger.error(f"Failed to create Chroma vector store: {e}")
-
-if __name__ == "__main__":
-    create_vector_store()
+import os
+import logging
+from langchain.document_loaders import PDFMinerLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import Chroma
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def create_vector_store():
+    documents = []
+    docs_dir = "docs"
+    if not os.path.exists(docs_dir):
+        logger.error(f"The directory '{docs_dir}' does not exist.")
+        return
+    
+    for root, dirs, files in os.walk(docs_dir):
+        for file in files:
+            if file.endswith(".pdf"):
+                file_path = os.path.join(root, file)
+                logger.info(f"Loading document: {file_path}")
+                try:
+                    loader = PDFMinerLoader(file_path)
+                    loaded_docs = loader.load()
+                    if loaded_docs:
+                        logger.info(f"Loaded {len(loaded_docs)} documents from {file_path}")
+                        documents.extend(loaded_docs)
+                    else:
+                        logger.warning(f"No documents loaded from {file_path}")
+                except Exception as e:
+                    logger.error(f"Error loading {file_path}: {e}")
+
+    if not documents:
+        logger.error("No documents were loaded. Check the 'docs' directory and file paths.")
+        return
+
+    logger.info(f"Loaded {len(documents)} documents.")
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+    logger.info(f"Created {len(texts)} text chunks.")
+
+    if not texts:
+        logger.error("No text chunks created. Check the text splitting process.")
+        return
+
+    try:
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        logger.info("Embeddings initialized successfully.")
+    except Exception as e:
+        logger.error(f"Failed to initialize embeddings: {e}")
+        return
+
+    try:
+        vector_store = Chroma.from_documents(texts, embeddings, persist_directory="./chroma_db")
+        vector_store.persist()
+        logger.info(f"Created Chroma vector store with {len(texts)} vectors.")
+    except Exception as e:
+        logger.error(f"Failed to create Chroma vector store: {e}")
+
+if __name__ == "__main__":
+    create_vector_store()