Multiple type of Loader RAG

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

app.py

@@ -0,0 +1,116 @@
+import streamlit as st
+from langchain_community.document_loaders import TextLoader, PyPDFLoader, WebBaseLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.llms import OpenAI
+from langchain.chains import RetrievalQA
+import os
+import tempfile
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_PROJECT"]="Multi Loader RAG"
+
+
+# Streamlit app title
+st.title("Multi Loader RAG")
+
+# File upload and web link input
+st.header("Upload Documents")
+text_file = st.file_uploader("Upload a Text File", type=["txt"])
+pdf_file = st.file_uploader("Upload a PDF File", type=["pdf"])
+web_link = st.text_input("Enter a Web URL")
+
+# Load documents function
+def load_documents(text_file, pdf_file, web_link):
+    docs = []
+    
+    # Load text file
+    if text_file is not None:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".txt") as tmp_file:
+            tmp_file.write(text_file.getvalue())
+            tmp_file_path = tmp_file.name
+        text_loader = TextLoader(tmp_file_path)
+        docs.extend(text_loader.load())
+        os.remove(tmp_file_path)
+    
+    # Load PDF file
+    if pdf_file is not None:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+            tmp_file.write(pdf_file.getvalue())
+            tmp_file_path = tmp_file.name
+        pdf_loader = PyPDFLoader(tmp_file_path)
+        docs.extend(pdf_loader.load())
+        os.remove(tmp_file_path)
+    
+    # Load web content
+    if web_link:
+        web_loader = WebBaseLoader([web_link])
+        docs.extend(web_loader.load())
+    
+    return docs
+
+# Split documents function
+def split_documents(docs, chunk_size, chunk_overlap):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=chunk_size,
+        chunk_overlap=chunk_overlap
+    )
+    return text_splitter.split_documents(docs)
+
+# Create FAISS vector store function
+def create_vector_store(splits):
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_documents(splits, embeddings)
+    return vectorstore
+
+# Main app logic
+if st.button("Process Documents"):
+    if not (text_file or pdf_file or web_link):
+        st.error("Please upload at least one document or provide a web link.")
+    else:
+        with st.spinner("Processing documents..."):
+            # Load documents
+            documents = load_documents(text_file, pdf_file, web_link)
+            
+            # Split documents
+            splits = split_documents(documents, 1000, 300)
+            
+            # Create FAISS vector store
+            st.session_state.vector_store = create_vector_store(splits)
+            
+            st.success("Documents processed and FAISS vector store created!")
+
+st.header("Get Summary/Answer")
+query = st.text_input("Enter your query")
+
+if st.button("Search"):
+    if st.session_state.vector_store is None:
+        st.error("Please process documents first.")
+    elif not query:
+        st.error("Please enter a query.")
+    else:
+        with st.spinner("Searching..."): 
+            # Create retriever and chain
+            retriever = st.session_state.vector_store.as_retriever(
+                search_type="similarity",
+                search_kwargs={"k": 5}
+            )
+            llm = OpenAI(temperature=0.6)
+            qa_chain = RetrievalQA.from_chain_type(
+                llm=llm,
+                chain_type="stuff",
+                retriever=retriever,
+                return_source_documents=True
+            )
+
+            # Execute query
+            result = qa_chain({"query": query})
+
+            # Display the result
+            st.markdown("### Answer:")
+            st.write(result["result"])

requirements.txt

@@ -0,0 +1,9 @@
+langchain
+python-dotenv
+langchain-openai
+langchain-community
+langchain-core
+bs4
+faiss-cpu
+streamlit
+pypdf