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

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

data/Data.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef945caf75b8219067ce06bd625f8581c60c54d58d071ef8355d9cba9294d84
+size 1378767

main.py

@@ -0,0 +1,121 @@
+
+import os
+from langchain_groq import ChatGroq
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+import time
+
+from typing import Union
+
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+app = FastAPI()
+
+
+from dotenv import load_dotenv
+import os
+load_dotenv()
+
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World"}
+
+
+class Query(BaseModel):
+    query_text: str
+
+
+## load the GROQ And OpenAI API KEY 
+groq_api_key=os.getenv('GROQ_API_KEY')
+os.environ["GOOGLE_API_KEY"]=os.getenv("GOOGLE_API_KEY")
+
+
+llm=ChatGroq(groq_api_key=groq_api_key,
+             model_name="Llama3-8b-8192")
+
+prompt=ChatPromptTemplate.from_template(
+"""
+Answer the questions based on the provided context only.
+Please provide the most accurate response based on the question
+<context>
+{context}
+<context>
+Questions:{input}
+
+"""
+)
+## load the GROQ And OpenAI API KEY 
+
+def vector_embedding():
+        embeddings=GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
+        loader=PyPDFDirectoryLoader("./data") ## Data Ingestion
+        docs=loader.load() ## Document Loading
+        text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200) ## Chunk Creation
+        final_documents=text_splitter.split_documents(docs[:20]) #splitting
+        vectors=FAISS.from_documents(final_documents,embeddings) #vector OpenAI embeddings
+        # dump the vectors as pickle file
+        vectors.save_local("vectors_db")
+
+
+
+
+@app.post("/groq")
+def read_item(query: Query):
+    try:
+        embeddings=GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
+        vectors = FAISS.load_local("vectors_db", embeddings,allow_dangerous_deserialization=True)
+    except:
+        # vector_embedding()
+        # vectors=FAISS.load("vectors.pkl")
+        print("Vector Store Not Found run /setup")
+        return {"response":"Vector Store Not Found run /setup"}
+    # print(vectors)
+    prompt1 = query.query_text
+    if prompt1:
+        start=time.process_time()
+        document_chain=create_stuff_documents_chain(llm,prompt)
+        retriever=vectors.as_retriever()
+        retrieval_chain=create_retrieval_chain(retriever,document_chain)
+        response=retrieval_chain.invoke({'input':prompt1})
+        print("Response time :",time.process_time()-start)
+        return response['answer']
+    else:
+        return {"response":"No Query Found"}
+    
+
+@app.get("/setup")
+def setup():
+    vector_embedding()
+    return {"response":"Vector Store DB Is Ready"}
+
+
+
+# if prompt1:
+#     document_chain=create_stuff_documents_chain(llm,prompt)
+#     # retriever=st.session_state.vectors.as_retriever()
+#     retrieval_chain=create_retrieval_chain(retriever,document_chain)
+#     start=time.process_time()
+#     response=retrieval_chain.invoke({'input':prompt1})
+#     print("Response time :",time.process_time()-start)
+#     st.write(response['answer'])
+
+    # # With a streamlit expander
+    # with st.expander("Document Similarity Search"):
+    #     # Find the relevant chunks
+    #     for i, doc in enumerate(response["context"]):
+    #         st.write(doc.page_content)
+    #         st.write("--------------------------------")
+
+
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -0,0 +1,13 @@
+faiss-cpu
+groq
+langchain-groq
+PyPDF2
+langchain_google_genai
+langchain
+# streamlit
+langchain_community
+python-dotenv
+pypdf
+google-cloud-aiplatform>=1.38
+fastapi
+uvicorn[standard]

vectors_db/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30048f3de2b8bbb4f14bee30bda4e80e2b558bb112aa27fe78e4ba4db61eedb
+size 74109