Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,16 @@
+# IDE Settings
+*.pyc
+.vscode
+.gradio
+.idea
+
+# Ignore environment file
+.env
+
+# Ignore Virtual Environment
+vsmpy-env/
+build/
+dist/
+
+# Ignore build file
+langchain_movie_search.spec

README.md

@@ -1,12 +1,7 @@
 ---
-title: Movie Search
-emoji: 🐢
-colorFrom: green
-colorTo: green
+title: Movie-Search
+app_file: langchain_movie_search.py
 sdk: gradio
-sdk_version: 5.12.0
-app_file: app.py
-pinned: false
+sdk_version: 5.3.0
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Vector-Search-Movies-Python

langchain_movie_search.py

@@ -0,0 +1,160 @@
+import os
+from typing import List
+import argparse
+from dotenv import load_dotenv
+import pymongo
+from langchain_huggingface import HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.documents import Document
+from langchain_core.prompts import PromptTemplate
+import gradio as gr
+from gradio.themes.base import Base
+from flask import Flask
+
+__author__ = "Chirag Kamble"
+
+
+# Flask App
+# app = Flask(__name__)
+
+
+class MoviesSearch:
+    """
+    Class to perform Vector Index Search using MongoDB and LLM search using Langchain on Movies
+    """
+
+    def __init__(self):
+        """
+        Initializing method
+        """
+        # Load environment variables
+        load_dotenv()
+        transformer_model_name: str = os.getenv("TRANSFORMER_MODEL_NAME")
+        mongodb_connection_url: str = os.getenv("MONGODB_CONNECTION_URL")
+        mongodb_db_name: str = os.getenv("MONGODB_DB_NAME")
+        mongodb_collection_name: str = os.getenv("MONGODB_COLLECTION_NAME")
+        self.huggingface_repo: str = os.getenv("HF_REPO")
+        self.huggingface_api_token: str = os.getenv("HF_TOKEN")
+        self.huggingface_text_generation_model: str = os.getenv("HUGGINGFACE_TEXT_GENERATION_MODEL")
+
+        # Setup MongoDB connection
+        self.client: pymongo.synchronous.mongo_client.MongoClient = pymongo.MongoClient(mongodb_connection_url,
+                                                                                        serverSelectionTimeoutMS=50000)
+        db: str = mongodb_db_name
+        collection_name: str = mongodb_collection_name
+        self.langchain_movies_collection: pymongo.synchronous.collection.Collection = self.client[db][collection_name]
+
+        self.sample_movies_collection: pymongo.synchronous.collection.Collection = self.client.sample_mflix.movies
+
+        self.hf_plot_embedding = HuggingFaceEmbeddings(
+            model_name=transformer_model_name,
+            show_progress=True,
+        )
+
+        self.retrieve_vector_store = MongoDBAtlasVectorSearch(collection=self.langchain_movies_collection,
+                                                              embedding=self.hf_plot_embedding,
+                                                              embedding_key="embedding",
+                                                              index_name="langchain_movies_vector_index",
+                                                              text_key="text",
+                                                              )
+
+    def generate_insert_embeddings(self):
+        """
+        Generate vector embeddings
+        """
+        new_doc_list: List[Document] = []
+        for doc in self.sample_movies_collection.find({"fullplot": {"$exists": True}}).limit(1000):
+            new_doc: Document = Document(
+                page_content=doc["fullplot"],
+                metadata={"source": "Collection sample_mflix",
+                          "movie-title": doc["title"],
+                          "movie-plot": doc["fullplot"],
+                          "text": doc["fullplot"]}
+            )
+            new_doc_list.append(new_doc)
+        self.retrieve_vector_store.from_documents(
+            documents=new_doc_list,
+            embedding=self.hf_plot_embedding,
+            collection=self.langchain_movies_collection
+        )
+
+    def query_data(self, query: str):
+        """
+        Query data from Atlas Vector Search
+        :param query: A user query to search
+        :return: String answer generated by the LLM
+        """
+        hf_llm: HuggingFaceEndpoint = HuggingFaceEndpoint(
+            repo_id=self.huggingface_text_generation_model,
+            huggingfacehub_api_token=self.huggingface_api_token,
+            temperature=0.1,
+            task="text-generation",
+            # max_new_tokens=100,
+            verbose=True,
+            return_full_text=True,
+        )
+
+        retriever = self.retrieve_vector_store.as_retriever()
+        prompt = PromptTemplate.from_template(template="{context}", template_format="f-string")
+        combine_docs = create_stuff_documents_chain(llm=hf_llm, prompt=prompt, )
+
+        retrival_chain = create_retrieval_chain(retriever=retriever, combine_docs_chain=combine_docs)
+        hf_llm_retriever_output = retrival_chain.invoke({"input": query})
+
+        llm_answer = hf_llm_retriever_output.get("answer")
+
+        return llm_answer
+
+    def run_website(self):
+        with gr.Blocks(theme=Base(), title="Movie plot search App using Vector Search + RAG") as v_search:
+            gr.Markdown("Movie plot search App using Vector Search + RAG")
+            textbox = gr.Textbox(label="Enter your question:", lines=1)
+            with gr.Row():
+                button = gr.Button("Submit", variant="primary")
+            with gr.Column():
+                output = gr.Textbox(lines=1, max_lines=10, interactive=False,
+                                    label="""Output generated by chaining Atlas Vector Search with Langchain's RAG""",)
+
+            button.click(fn=self.query_data, inputs=textbox, outputs=[output])
+
+        v_search.launch(share=True)
+
+    def close_client(self):
+        self.client.close()
+
+
+# @app.route("/", methods=["GET"])
+def gradio_interface(cmd=None):
+    movie_search = MoviesSearch()
+    movie_search.generate_insert_embeddings()
+    movie_search.run_website()
+
+    # if cmd == "generate_embeddings":
+    #     movie_search.generate_insert_embeddings()
+    # elif cmd == "run":
+    #     movie_search.run_website()
+
+
+if __name__ == "__main__":
+    # Create the parser
+    # parser = argparse.ArgumentParser(description='Script to suggest movies based on user description/query')
+    #
+    # # Add arguments
+    # parser.add_argument("-g", "--generate_embeddings", action="store_true", help="Generate/Re-generate Embeddings")
+    # parser.add_argument("-r", "--run", action="store_true", help="Age of the person")
+    #
+    # # Parse arguments
+    # args = parser.parse_args()
+    #
+    # if args.generate_embeddings:
+    #     gradio_interface(cmd="generate_embeddings")
+    # elif args.run:
+    #     gradio_interface(cmd="run")
+
+    # app.run(host="0.0.0.0", port=os.getenv("PORT", 5000), debug=True)
+    # app.run(host="0.0.0.0", debug=True)
+    # app.run(debug=True)
+
+    gradio_interface()

requirements.txt

@@ -0,0 +1,138 @@
+#Install all packages to run the code
+
+# MongoDB
+dnspython==2.7.0
+pymongo==4.10.1
+
+# Requests
+certifi==2024.8.30
+charset-normalizer==3.4.0
+idna==3.10
+requests==2.32.3
+urllib3==2.2.3
+
+#Environment
+python-dotenv==1.0.1
+
+# Sentence-Transformer
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+sentence-transformers==3.2.1
+sympy==1.13.1
+threadpoolctl==3.5.0
+tokenizers==0.20.1
+torch==2.5.0
+tqdm==4.66.5
+transformers==4.45.2
+typing_extensions==4.12.2
+certifi==2024.8.30
+charset-normalizer==3.4.0
+colorama==0.4.6
+dnspython==2.7.0
+filelock==3.16.1
+fsspec==2024.10.0
+huggingface-hub==0.26.1
+idna==3.10
+Jinja2==3.1.4
+joblib==1.4.2
+# MarkupSafe==3.0.2
+mpmath==1.3.0
+networkx==3.4.2
+packaging==24.1
+# pillow==11.0.0
+
+# Setup tools
+setuptools==75.2.0
+PyYAML==6.0.2
+regex==2024.9.11
+# numpy==2.1.2
+
+# Langchain
+SQLAlchemy==2.0.36
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+attrs==24.2.0
+frozenlist==1.5.0
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.4
+langchain-core==0.3.12
+langchain-text-splitters==0.3.0
+langsmith==0.1.137
+multidict==6.1.0
+numpy==1.26.4
+orjson==3.10.10
+propcache==0.2.0
+pydantic==2.9.2
+pydantic-core==2.23.4
+requests-toolbelt==1.0.0
+sniffio==1.3.1
+tenacity==9.0.0
+yarl==1.16.0
+
+# Langchain HuggingFace
+langchain-HuggingFace==0.1.0
+
+# Lnagchain Mongodb
+langchain-mongodb==0.2.0
+
+# Langchain Community
+dataclasses-json==0.6.7
+langchain_community==0.3.3
+marshmallow==3.23.0
+mypy-extensions==1.0.0
+pydantic-settings==2.6.0
+typing-inspect==0.9.0
+
+# Gradio
+aiofiles==23.2.1
+click==8.1.7
+fastapi==0.115.3
+ffmpy==0.4.0
+gradio==5.3.0
+gradio-client==1.4.2
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+pandas==2.2.3
+pillow==10.4.0
+pydub==0.25.1
+pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+rich==13.9.3
+ruff==0.7.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+starlette==0.41.0
+tomlkit==0.12.0
+typer==0.12.5
+tzdata==2024.2
+uvicorn==0.32.0
+websockets==12.0
+
+# Flask
+Werkzeug==3.0.6
+blinker==1.8.2
+flask==3.0.3
+itsdangerous==2.2.0
+
+# Pyinstaller
+altgraph==0.17.4
+pefile==2023.2.7
+pyinstaller==6.11.0
+pyinstaller-hooks-contrib==2024.9
+pywin32-ctypes==0.2.3
+
+# Gunicorn
+gunicorn==23.0.0

temp_req.txt

@@ -0,0 +1,103 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+altgraph==0.17.4
+annotated-types==0.7.0
+anyio==4.6.2.post1
+attrs==24.2.0
+blinker==1.8.2
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+colorama==0.4.6
+dataclasses-json==0.6.7
+dnspython==2.7.0
+fastapi==0.115.3
+ffmpy==0.4.0
+filelock==3.16.1
+Flask==3.0.3
+frozenlist==1.5.0
+fsspec==2024.10.0
+gradio==5.3.0
+gradio_client==1.4.2
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.26.1
+idna==3.10
+itsdangerous==2.2.0
+Jinja2==3.1.4
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.4
+langchain-community==0.3.3
+langchain-core==0.3.12
+langchain-huggingface==0.1.0
+langchain-mongodb==0.2.0
+langchain-text-splitters==0.3.0
+langsmith==0.1.137
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.23.0
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+networkx==3.4.2
+numpy==1.26.4
+orjson==3.10.10
+packaging==24.1
+pandas==2.2.3
+pefile==2023.2.7
+pillow==10.4.0
+propcache==0.2.0
+pydantic==2.9.2
+pydantic-settings==2.6.0
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyinstaller==6.11.0
+pyinstaller-hooks-contrib==2024.9
+pymongo==4.10.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.12
+pytz==2024.2
+pywin32-ctypes==0.2.3
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==13.9.3
+ruff==0.7.1
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+sentence-transformers==3.2.1
+setuptools==75.2.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+SQLAlchemy==2.0.36
+starlette==0.41.0
+sympy==1.13.1
+tenacity==9.0.0
+threadpoolctl==3.5.0
+tokenizers==0.20.1
+tomlkit==0.12.0
+torch==2.5.0
+tqdm==4.66.5
+transformers==4.45.2
+typer==0.12.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+websockets==12.0
+Werkzeug==3.0.6
+yarl==1.16.0