Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+imdb_datasets.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,17 @@
----
-title: Codepath
-emoji: 📉
-colorFrom: indigo
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# RAG Llm Project
+
+This is a Python project for the RAG Llm project. It utilizes movie data to return relevant information.
+
+## Installation
+
+To use this project, follow these steps:
+
+1. Clone the repository: `git clone https://github.com/your-username/rag-llm-project.git`
+2. Install the required dependencies: `pip install -r requirements.txt`
+Set up your environment variables by creating a .env file with your OPENAI_API_KEY and ASSISTANT_ID.
+
+## Usage
+
+To run the project, execute the following command:
+
+Start the Chainlit app by running app.py.

app.py

@@ -0,0 +1,29 @@
+
+import os
+from rag import RAGModel
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+from langchain.schema import StrOutputParser
+from langchain.chains import LLMChain
+
+import chainlit as cl
+
+# Get the value of OPEN_API_KEY from the environment
+
+rag = RAGModel(os.getenv("OPENAI_API_KEY"))
+
+
+@cl.on_chat_start
+async def on_chat_start():
+    msg=cl.Message(content="Firing up the research info bot...")
+    await msg.send()
+    msg.content= "Hi, welcome to research info bot. What is your query?"
+    await msg.update()
+
+
+@cl.on_message
+async def on_message(message: cl.Message):
+    answer = rag.query(question=message.content)
+    await cl.Message(content=answer).send()
+
+

chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

imdb_datasets.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a55444797da9627738b3f2a8985dc0e6fa5ddb50516ee66e2c3e2e8b389b7a
+size 10753100

rag.py

@@ -0,0 +1,104 @@
+import os
+from langchain_core.runnables.base import RunnableSequence
+from langchain_core.runnables.passthrough import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain_community.document_loaders import CSVLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.storage import LocalFileStore
+from langchain_community.vectorstores import FAISS
+
+# PIP Install the following packages:
+# pip install -q langchain
+# pip install -q langchain_openai
+# pip install -q faiss-cpu tiktoken 
+# pip install -q -U langchain
+# pip install -U langchain-community
+
+class RAGModel:
+    def __init__(self, api_key):
+        self.api_key = api_key
+        # for the RAG model. First we need to get the Dcouments processed to be used as context for the model.
+       
+        # Load DataSet
+        csv_file = "imdb_datasets.csv"
+        loader = CSVLoader(csv_file)
+        csv_data = loader.load()
+       
+        # 1. Split the dataset
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+        chunked_documents = text_splitter.split_documents(csv_data)
+        print(f"Number of documents: {len(chunked_documents)}")
+        #len(chunked_documents) # ensure we have actually split the data into chunks
+       
+        # 2. Create embeddings
+        embedding_model = OpenAIEmbeddings(model="text-embedding-3-large", openai_api_key=self.api_key)
+        print("Created embeddings")
+       
+        # Create a cache backed embeddings
+        local_store = LocalFileStore("./cache/")
+        cached_embedder = CacheBackedEmbeddings.from_bytes_store(embedding_model, local_store, namespace=embedding_model.model)
+        print("Created cache backed embeddings")
+       
+        # 3. Save the documents in the vector store as embeddings
+
+        self.vector_store = FAISS.from_documents(chunked_documents, cached_embedder)
+        self.vector_store.save_local("faiss_index")
+
+        # 3. Retrive the vector store
+        # create a retriever
+        retriever = self.vector_store.as_retriever()
+
+        # 4. Create a prompt - LangChain
+        # The prompt has place for the context from the raq and the question from the user
+        prompt_template = ChatPromptTemplate.from_messages(
+            [
+                ("system", "You are an excellent movie critic who always includes great movie recommendations in your response. If the answer is not in the context let the user know "),
+                ("human", "Using this context: {context}, please answer this question: {question}")
+            ]
+        )
+        
+        chat_model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0, api_key=api_key)
+        parser = StrOutputParser()
+
+        self.runnable_chain = (
+            {
+                "context": retriever,
+                "question": RunnablePassthrough(),
+            }
+            | prompt_template
+            | chat_model
+            | parser
+        ) 
+        
+    def query(self, question) -> str:
+        print(f"Querying the RAG instance with the question: {question}")
+        output_chunks = self.runnable_chain.invoke(question)
+        return ''.join(output_chunks)
+        
+        
+# def main():
+    # Create an instance of RAG class
+    # api_key = os.getenv("OPENAI_API_KEY")
+    # rag = RAGModel(api_key=api_key)
+    
+    # while True:
+    #     # Take input from command line
+    #     question = input("Enter your question (or type 'exit' to quit): ")
+        
+    #     # Check if user wants to exit
+    #     if question.lower() == "exit":
+    #         break
+        
+    #     # Query the RAG instance
+    #     answer = rag.query(question)
+        
+    #     # Print the answer
+    #     print("Answer:", answer)
+    
+    
+# if __name__ == "__main__":    
+#     main()

requirements.txt

@@ -0,0 +1,87 @@
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==3.7.1
+asyncer==0.0.2
+attrs==23.2.0
+bidict==0.23.1
+certifi==2024.2.2
+chainlit==1.1.101
+charset-normalizer==3.3.2
+chevron==0.14.0
+click==8.1.7
+dataclasses-json==0.5.14
+Deprecated==1.2.14
+distro==1.9.0
+faiss-cpu==1.8.0
+fastapi==0.110.3
+fastapi-socketio==0.0.10
+filetype==1.2.0
+frozenlist==1.4.1
+googleapis-common-protos==1.63.0
+greenlet==3.0.3
+grpcio==1.64.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+idna==3.7
+importlib-metadata==7.0.0
+jsonpatch==1.33
+jsonpointer==2.4
+langchain==0.2.0
+langchain-community==0.2.0
+langchain-core==0.2.0
+langchain-openai==0.1.7
+langchain-text-splitters==0.2.0
+langsmith==0.1.60
+Lazify==0.4.0
+literalai==0.0.601
+marshmallow==3.21.2
+multidict==6.0.5
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+numpy==1.26.4
+openai==1.30.1
+opentelemetry-api==1.24.0
+opentelemetry-exporter-otlp==1.24.0
+opentelemetry-exporter-otlp-proto-common==1.24.0
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+opentelemetry-exporter-otlp-proto-http==1.24.0
+opentelemetry-instrumentation==0.45b0
+opentelemetry-proto==1.24.0
+opentelemetry-sdk==1.24.0
+opentelemetry-semantic-conventions==0.45b0
+orjson==3.10.3
+packaging==23.2
+protobuf==4.25.3
+pydantic==2.7.1
+pydantic_core==2.18.2
+PyJWT==2.8.0
+python-dotenv==1.0.1
+python-engineio==4.9.1
+python-multipart==0.0.9
+python-socketio==5.11.2
+PyYAML==6.0.1
+regex==2024.5.15
+requests==2.32.0
+setuptools==69.5.1
+simple-websocket==1.0.0
+sniffio==1.3.1
+SQLAlchemy==2.0.30
+starlette==0.37.2
+syncer==2.0.3
+tenacity==8.3.0
+tiktoken==0.7.0
+tomli==2.0.1
+tqdm==4.66.4
+typing-inspect==0.9.0
+typing_extensions==4.11.0
+uptrace==1.24.0
+urllib3==2.2.1
+uvicorn==0.25.0
+watchfiles==0.20.0
+wrapt==1.16.0
+wsproto==1.2.0
+yarl==1.9.4
+zipp==3.18.2