Upload 8 files

added a sample RAG test for generating question based on `yolo paper.pdf`
**Data folder** : contain the PDF to Retrieve from
**SimpleRAG_test** : notebook for trials
**src** : containing the helper function and the system prompt to be used
**app.py** : running the app

.env

@@ -0,0 +1,3 @@
+PINECONE_API_KEY = "pcsk_3Yn1k3_CGnRMFtjNPnzh62rmQtogLwjXnEBey3ygLeAf3pphuVbcgdraDaENNWM8L4oz5"
+OPENAI_API_KEY = "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"
+GOOGLE_API_KEY = "AIzaSyADUTjZIpL_MXiBEAZD17DgE3zbmr5I8oU"

.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
+Data/yolov9_paper.pdf filter=lfs diff=lfs merge=lfs -text

Data/yolov9_paper.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a67aef4802df6f1e32f84884b309b59818294df56b4dafe1c097287b222e9fd
+size 4968643

app.py

@@ -0,0 +1,72 @@
+import streamlit as st
+
+# from src.helper import download_hugging_face_embeddings
+
+from langchain_pinecone import PineconeVectorStore
+from langchain_openai import OpenAI
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_huggingface import HuggingFaceEmbeddings
+from src.prompt import *
+
+from dotenv import load_dotenv
+import os
+
+
+#Download the Embeddings from Hugging Face
+def download_hugging_face_embeddings():
+    embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+    return embeddings
+
+
+# Load env Variables
+load_dotenv()
+
+PINECONE_API_KEY=os.environ.get('PINECONE_API_KEY')
+OPENAI_API_KEY=os.environ.get('OPENAI_API_KEY')
+GOOGLE_API_KEY= os.environ.get("GOOGLE_API_KEY")
+
+os.environ["PINECONE_API_KEY"] = PINECONE_API_KEY
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+os.environ["GOOGLE_API_KEY"] = GOOGLE_API_KEY
+# Embedding model
+embeddings = download_hugging_face_embeddings()
+
+
+# load exisiting pinecone index
+index_name = "yolotest"
+Vector_store = PineconeVectorStore.from_existing_index(
+    index_name=index_name,
+    embedding=embeddings
+)
+
+# Retriever
+retriever = Vector_store.as_retriever(search_type="similarity", search_kwargs={"k":5})
+
+# llm
+# llm = OpenAI(api_key=OPENAI_API_KEY, temperature=0, max_tokens=500)
+llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro",temperature=0,max_tokens=None,timeout=None)
+
+# streamlit 
+st.title("RAG Application built on Gemini Model")
+query = st.chat_input("Say something: ") 
+prompt = query
+
+
+prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", system_prompt),
+        ("human", "{input}"),
+    ]
+)
+
+
+if query:
+    question_answer_chain = create_stuff_documents_chain(llm, prompt)
+    rag_chain = create_retrieval_chain(retriever, question_answer_chain)
+
+    response = rag_chain.invoke({"input": query})
+
+    st.write(response["answer"])

requirements.txt

@@ -0,0 +1,12 @@
+langchain
+langchain-community
+langchain_huggingface
+langchain-pinecone
+langchain_openai
+pypdf
+streamlit
+pinecone
+sentence-transformers
+python-dotenv
+langchain_experimental
+langchain-google-genai

src/__init__.py

@@ -0,0 +1 @@
+# from helpers import download_hugging_face_embeddings

src/helpers.py

@@ -0,0 +1,29 @@
+from langchain_community.document_loaders import TextLoader, PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
+
+
+#Extract Data From the PDF File
+def load_pdf_file(data):
+    loader= DirectoryLoader(data,
+                            glob="*.pdf",
+                            loader_cls=PyPDFLoader)
+
+    documents=loader.load()
+
+    return documents
+
+
+#Split the Data into Text Chunks
+def text_split(extracted_data):
+    text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    text_chunks=text_splitter.split_documents(extracted_data)
+    return text_chunks
+
+
+
+
+#Download the Embeddings from Hugging Face
+def download_hugging_face_embeddings():
+    embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+    return embeddings

src/prompt.py

@@ -0,0 +1,11 @@
+system_prompt = (
+    "You are a AI expert who can generate questions from retrieved docs. "
+    "You will be given a topic to generate question about"
+    "Use the following pieces of retrieved context to generate "
+    "new questions based on the topic given."
+    "say that you don't know if the input given is beyond the scope of the retrieved context "
+    " dont respond with anything accept for generated question"
+    "Use three sentences maximum and keep the generated questions concise."
+    "\n\n"
+    "{context}"
+)