Add code with the opensource model as well

.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

README.md

@@ -1,14 +1,19 @@
----
-title: Research Paper Summerizer
-emoji: 🌍
-colorFrom: yellow
-colorTo: indigo
-sdk: streamlit
-sdk_version: 1.42.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: Summarise the pdf based research paper
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Research Paper Summarizer
+
+This app uses Hugging Face's model and LangChain to process research papers in PDF format and generate summaries or answers to queries.
+
+## Features
+- Upload multiple research PDFs
+- Create vector databases using FAISS
+- Ask questions or request summaries from research content
+- Powered by Hugging Face's model
+
+## How to Use
+1. Upload one or more PDFs.
+2. Click the **Process PDFs** button to create a vector store.
+3. Enter your query or summary request.
+4. Click **Get Summary/Answer** to generate a response.
+
+## Requirements
+- Python 3.10+
+- Hugging Face Space environment

app-open-source-models.py

@@ -0,0 +1,127 @@
+import os
+import tempfile
+import streamlit as st
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from io import BytesIO
+from langchain.document_loaders import PyPDFLoader
+from transformers import pipeline
+from langchain.schema import Document
+from dotenv import load_dotenv
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+# Load environment variables from Hugging Face Secrets
+load_dotenv()
+
+os.environ['HUGGINGFACE_API_KEY'] = os.getenv("HF_TOKEN")
+os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_PROJECT"]="Research-Paper-Summarizer"
+
+# Streamlit Page Config
+st.set_page_config(
+    page_title="Research Paper Summarizer",
+    layout="centered"
+)
+
+st.title("📚 Research Paper Summarizer - Using Open Source Models")
+
+# File Uploader
+uploaded_files = st.file_uploader(
+    "Upload one or more research PDFs",
+    type=["pdf"],
+    accept_multiple_files=True
+)
+
+# A placeholder to store vector database (FAISS)
+if "vector_store" not in st.session_state:
+    st.session_state.vector_store = None
+
+# Hugging Face LLM Model Pipeline
+def get_huggingface_pipeline():
+    
+    model_name = "meta-llama/Llama-3.2-1B"
+    
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    
+    st.info("Loading Hugging Face Model... Please wait.")
+    
+    return transformers.pipeline(
+        "text-generation",
+        model=model_name,
+        tokenizer=tokenizer,
+        max_new_tokens=256, 
+        torch_dtype=torch.bfloat16
+)
+
+
+# Process the PDFs, Create/Update the Vector Store
+if st.button("Process PDFs") and uploaded_files:
+    all_documents = []
+
+    for file in uploaded_files:
+        # Save the file temporarily
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
+            temp_file.write(file.getvalue())
+            temp_file_path = temp_file.name
+
+        # Load the PDF using PyPDFLoader
+        loader = PyPDFLoader(temp_file_path)
+        pdf_docs = loader.load()
+
+        # Split text into manageable chunks
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1000,
+            chunk_overlap=300,
+            separators=["\n\n", "\n", " ", ""]
+        )
+
+        for doc in pdf_docs:
+            chunks = text_splitter.split_text(doc.page_content)
+            for chunk in chunks:
+                # Create Document object for each chunk
+                all_documents.append(Document(page_content=chunk, metadata=doc.metadata))
+
+    # Create embeddings with Hugging Face
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    st.session_state.vector_store = FAISS.from_documents(
+        documents=all_documents,
+        embedding=embeddings
+    )
+
+    st.success("PDFs processed and vector store created!")
+
+# Query + Summarize
+query = st.text_input("Enter your question or summary request:")
+
+if st.button("Get Summary/Answer"):
+    if st.session_state.vector_store is None:
+        st.warning("Please upload and process PDFs first.")
+    else:
+        retriever = st.session_state.vector_store.as_retriever(
+            search_type="similarity",
+            search_kwargs={"k": 5}
+        )
+
+        # Use Hugging Face LLM
+        hf_pipeline = get_huggingface_pipeline()
+
+        # Retrieve documents and generate response
+        relevant_docs = retriever.get_relevant_documents(query)
+        context_text = "\n".join([doc.page_content for doc in relevant_docs])
+
+        # Generate answer using Hugging Face model
+        response = hf_pipeline(f"Context: {context_text}\nQuestion: {query}", num_return_sequences=1)
+
+        st.markdown("### Answer:")
+        st.write(response[0]['generated_text'])
+
+        with st.expander("Show source documents"):
+            for i, doc in enumerate(relevant_docs):
+                st.markdown(f"**Source Document {i + 1}:**")
+                st.write(doc.page_content)
+                st.write("---")

app.py

@@ -13,7 +13,6 @@ from dotenv import load_dotenv
 # Load environment variables
 load_dotenv()
 
-os.environ['OPENAI_API_KEY'] = os.getenv("OPENAI_API_KEY")
 os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")
 os.environ["LANGCHAIN_TRACING_V2"] = "true"
 os.environ["LANGCHAIN_PROJECT"]="Research-Paper-Summarizer"