First commit

app.py

@@ -0,0 +1,74 @@
+import os
+import gradio as gr
+from pinecone import Pinecone
+from langchain_chroma import Chroma
+from langchain_core.prompts import PromptTemplate
+from langchain_pinecone import PineconeVectorStore
+from langchain_community.vectorstores import FAISS
+from langchain_community.vectorstores import LanceDB
+from langchain_text_splitters import CharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, GoogleGenerativeAI
+
+embeddings = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")
+gemini = GoogleGenerativeAI(model="models/gemini-2.0-flash")
+
+prompt_template = """
+    
+    Context:\n {context}?\n
+    Question: \n{question}\n
+
+    Answer:
+    """
+
+prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])
+
+chain = prompt | gemini
+
+def inference(pdf_path, chunk_size, chunk_overlap):
+    raw_documents = PyPDFLoader(pdf_path).load()
+    text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
+    documents = text_splitter.split_documents(raw_documents)
+
+    pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
+
+    index_name = "langchain-test-index"
+
+    index = pc.Index(host="https://langchain-test-index-la2n80y.svc.aped-4627-b74a.pinecone.io")
+
+    index.delete(delete_all=True)
+
+    chroma_db = Chroma.from_documents(documents, embeddings, persist_directory="./chroma_db")
+    faiss_db = FAISS.from_documents(documents, embeddings)
+    faiss_db.save_local("./faiss_db")
+    lance_db = LanceDB.from_documents(documents, embeddings, uri="./lance_db")
+    pinecone_db = PineconeVectorStore.from_documents(documents, index_name=index_name,
+                                                     embedding=embeddings)
+    
+    return "All embeddings are stored in vector database"
+
+title = "PDF Chat"
+description = "A simple Gradio interface to query PDFs and compare vector database"
+examples = [["data/amazon-10-k-2024.pdf", 1000, 100],
+            ["data/goog-10-k-2023.pdf", 1000, 100]]
+
+with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
+    gr.Markdown(f"# {title}\n{description}")
+    with gr.Row():
+        with gr.Column():
+            pdf = gr.UploadButton(file_types=[".pdf"])
+            chunk_size = gr.Slider(0, 2000, 1000, 100, label="Size of Chunk")
+            chunk_overlap = gr.Slider(0, 1000, 100, 100, label="Size of Chunk Overlap")
+            with gr.Row():
+                clear_btn = gr.ClearButton(components=[pdf, chunk_size, chunk_overlap])
+                submit_btn = gr.Button("Store Embeddings", variant='primary')
+        with gr.Column():
+            message = gr.Textbox(label="Status", type="text")
+
+    submit_btn.click(inference, inputs=[pdf, chunk_size, chunk_overlap], outputs=message)
+
+demo.launch()
+    
+
+    
+    

requirements.txt

@@ -0,0 +1,154 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.6.1
+aiohttp==3.10.11
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.8.0
+asgiref==3.8.1
+attrs==25.3.0
+audioop-lts==0.2.1
+backoff==2.2.1
+bcrypt==4.3.0
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.1.31
+charset-normalizer==3.4.1
+chroma-hnswlib==0.7.6
+chromadb==0.6.3
+click==8.1.8
+colorama==0.4.6
+coloredlogs==15.0.1
+dataclasses-json==0.6.7
+Deprecated==1.2.18
+deprecation==2.1.0
+distro==1.9.0
+durationpy==0.9
+fastapi==0.115.11
+ffmpy==0.5.0
+filelock==3.18.0
+filetype==1.2.0
+flatbuffers==25.2.10
+frozenlist==1.5.0
+fsspec==2025.3.0
+google-ai-generativelanguage==0.6.16
+google-api-core==2.24.2
+google-auth==2.38.0
+googleapis-common-protos==1.69.1
+gradio==5.21.0
+gradio_client==1.7.2
+greenlet==3.1.1
+groovy==0.1.2
+grpcio==1.71.0
+grpcio-status==1.71.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.29.3
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+iniconfig==2.0.0
+Jinja2==3.1.6
+jsonpatch==1.33
+jsonpointer==3.0.0
+kubernetes==32.0.1
+lancedb==0.21.1
+langchain==0.3.20
+langchain-chroma==0.2.2
+langchain-community==0.3.19
+langchain-core==0.3.45
+langchain-google-genai==2.1.0
+langchain-pinecone==0.2.3
+langchain-tests==0.3.14
+langchain-text-splitters==0.3.6
+langsmith==0.3.15
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.26.1
+mdurl==0.1.2
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.21.0
+opentelemetry-api==1.31.0
+opentelemetry-exporter-otlp-proto-common==1.31.0
+opentelemetry-exporter-otlp-proto-grpc==1.31.0
+opentelemetry-instrumentation==0.52b0
+opentelemetry-instrumentation-asgi==0.52b0
+opentelemetry-instrumentation-fastapi==0.52b0
+opentelemetry-proto==1.31.0
+opentelemetry-sdk==1.31.0
+opentelemetry-semantic-conventions==0.52b0
+opentelemetry-util-http==0.52b0
+orjson==3.10.15
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pillow==11.1.0
+pinecone==5.4.2
+pinecone-plugin-inference==3.1.0
+pinecone-plugin-interface==0.0.7
+pluggy==1.5.0
+posthog==3.20.0
+propcache==0.3.0
+proto-plus==1.26.1
+protobuf==5.29.3
+pyarrow==19.0.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.10.6
+pydantic-settings==2.8.1
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.19.1
+pylance==0.24.1
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+pyreadline3==3.5.4
+pytest==8.3.5
+pytest-asyncio==0.25.3
+pytest-socket==0.7.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.20
+pytz==2025.1
+PyYAML==6.0.2
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==13.9.4
+rsa==4.9
+ruff==0.11.0
+safehttpx==0.1.6
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.39
+starlette==0.46.1
+sympy==1.13.3
+syrupy==4.9.0
+tenacity==9.0.0
+tokenizers==0.21.1
+tomlkit==0.13.2
+tqdm==4.67.1
+typer==0.15.2
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+uvicorn==0.34.0
+watchfiles==1.0.4
+websocket-client==1.8.0
+websockets==15.0.1
+wrapt==1.17.2
+yarl==1.18.3
+zipp==3.21.0
+zstandard==0.23.0