Merge pull request #877 from oracle-devrel/newRAGCode

changes on doc summarization and new files in rag

Author: al3xne

ai-and-app-modernisation/ai-services/generative-ai-service/rag-genai/files/LangChainRAG.py

@@ -0,0 +1,21 @@
+from langchain_community.embeddings import OCIGenAIEmbeddings
+from langchain.chains import RetrievalQA
+from langchain_community.vectorstores import Qdrant
+from langchain_core.prompts import PromptTemplate
+from langchain_community.llms import OCIGenAI
+from langchain_community.document_loaders import UnstructuredURLLoader
+compartment_id = "ocid1.compartment.oc1..aaaaaaaa7ggqkd4ptkeb7ugk6ipsl3gqjofhkr6yacluwj4fitf2ufrdm65q"
+embeddings = OCIGenAIEmbeddings(model_id="cohere.embed-english-light-v3.0",service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",compartment_id= compartment_id,)
+testurls = ['https://docs.oracle.com/iaas/odsaz/odsa-rotate-wallet.html', 'https://docs.oracle.com/iaas/odsaz/odsa-change-password.html', 'https://docs.oracle.com/iaas/odsaz/odsa-database-actions.html']
+loader = UnstructuredURLLoader(urls=testurls)
+docs = loader.load()
+vectorstore = Qdrant.from_documents(docs,embeddings,location=":memory:",prefer_grpc=False,collection_name="test_db")
+retriever = vectorstore.as_retriever()
+rag_prompt_template = """Answer the question based only on the following context:
+{context}
+Question: {question}"""
+rag_prompt = PromptTemplate.from_template(rag_prompt_template)
+llm = OCIGenAI(model_id="cohere.command",service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",compartment_id= compartment_id,model_kwargs={"temperature": 0, "max_tokens": 300})
+rag = RetrievalQA.from_chain_type(llm=llm,retriever=retriever,chain_type_kwargs={"prompt": rag_prompt,},)
+data = rag.invoke("What is rotate a wallet")
+print(data['result'])

ai-and-app-modernisation/ai-services/generative-ai-service/rag-genai/files/README.md

@@ -3,30 +3,27 @@
 ## Introduction
 In this article, we'll explore how to create a Retrieval-Augmented Generation (RAG) model using Oracle Gen AI, llama index, Qdrant Vector Database, and SentenceTransformerEmbeddings. This 21-line code will allow you to scrape through web pages, use llama index for indexing, Oracle Generative AI Service for question generation, and Qdrant for vector indexing.
 
+Find below the code of building a RAG using llamaIndex with Oracle Generative AI Service.
+Also check the file LangChainRAG.py which allows you to create an application (implementing RAG) using Langchain and the file langChainRagWithUI.py which includes a UI build with Streamlit.
+
 <img src="./RagArchitecture.svg">
 </img>
 
-## Limited Availability
-
-Oracle Generative AI Service is in Limited Availability as of today when we are creating this repo.
-
-Customers can easily enter in the LA programs. To test these functionalities you need to enrol in the LA programs and install the proper versions of software libraries.
-
-Code and functionalities can change, as a result of changes and new features
-
 ## Prerequisites
 
 Before getting started, make sure you have the following installed:
 
 - Oracle Generative AI Service
-- llama index
-- qdrant client
+- Llama index
+- Langchain
+- Qdrant client
 - SentenceTransformerEmbeddings
 
 ## Setting up the Environment
 1. Install the required packages:
    ```bash
-   pip install oci==2.118.1+preview.1.1697 llama-index qdrant-client sentence-transformers
+   pip install -U langchain oci
+   pip install langchain llama-index qdrant-client sentence-transformers transformers
    ```
 
 ## Loading data
@@ -41,26 +38,26 @@ sitemap used : https://objectstorage.eu-frankfurt-1.oraclecloud.com/n/frpj5kvxry
 ## Entire code
 
    ```bash
-   from genai_langchain_integration.langchain_oci import OCIGenAI
 from llama_index import VectorStoreIndex
 from llama_index import ServiceContext
 from llama_index.vector_stores.qdrant import QdrantVectorStore
 from llama_index.storage.storage_context import StorageContext
 from qdrant_client import qdrant_client
-from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain_community.embeddings import SentenceTransformerEmbeddings
 from llama_hub.web.sitemap import SitemapReader
+from langchain_community.llms import OCIGenAI
 loader = SitemapReader()
-documents = loader.load_data(sitemap_url='https://objectstorage.eu-frankfurt-1.oraclecloud.com/n/frpj5kvxryk1/b/thisIsThePlace/o/combined.xml')
+documents = loader.load_data(sitemap_url='https://objectstorage.eu-frankfurt-1.oraclecloud.com/n/frpj5kvxryk1/b/thisIsThePlace/o/latest.xml')
 client = qdrant_client.QdrantClient(location=":memory:")
 embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
-llm = OCIGenAI(model_id="cohere.command",service_endpoint="https://generativeai.aiservice.us-chicago-1.oci.oraclecloud.com",compartment_id = "ocid1.tenancy.oc1..aaaaaaaa5hwtrus75rauufcfvtnjnz3mc4xm2bzibbigva2bw4ne7ezkvzha",temperature=0.0)
+llm = OCIGenAI(model_id="cohere.command",service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",model_kwargs={"temperature": 0.0, "max_tokens": 300},compartment_id = "ocid1.compartment.oc1..aaaaaaaa7ggqkd4ptkeb7ugk6ipsl3gqjofhkr6yacluwj4fitf2ufrdm65q")
 system_prompt="As a support engineer, your role is to leverage the information in the context provided. Your task is to respond to queries based strictly on the information available in the provided context. Do not create new information under any circumstances. Refrain from repeating yourself. Extract your response solely from the context mentioned above. If the context does not contain relevant information for the question, respond with 'How can I assist you with questions related to the document?"
 service_context = ServiceContext.from_defaults(llm=llm, chunk_size=1000, chunk_overlap=100, embed_model=embeddings,system_prompt=system_prompt)
 vector_store = QdrantVectorStore(client=client, collection_name="ansh")
 storage_context = StorageContext.from_defaults(vector_store=vector_store)
 index = VectorStoreIndex.from_documents(documents, storage_context=storage_context, service_context=service_context)
 query_engine = index.as_query_engine()
-response = query_engine.query("can i use OCI document understanding for files in french ?")
+response = query_engine.query('What is activity auditing report?')
 print(response)
    ```
 

ai-and-app-modernisation/ai-services/generative-ai-service/rag-genai/files/langChainRagWithUI.py

@@ -0,0 +1,42 @@
+import streamlit as st
+from langchain_community.embeddings import OCIGenAIEmbeddings
+from langchain.chains import RetrievalQA
+from langchain_community.vectorstores import Qdrant
+from langchain_core.prompts import PromptTemplate
+from langchain_community.llms import OCIGenAI
+from langchain_community.document_loaders import UnstructuredURLLoader
+st.title("Oracle QA Chatbot")
+st.text_input("Ask a question:", key="question")  # Input field for questions
+# Data loading (outside any function)
+compartment_id = "ocid1.compartment.oc1..aaaaaaaa7ggqkd4ptkeb7ugk6ipsl3gqjofhkr6yacluwj4fitf2ufrdm65q"
+embeddings = OCIGenAIEmbeddings(model_id="cohere.embed-english-light-v3.0",service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",compartment_id=compartment_id,)
+testurls = ['https://docs.oracle.com/iaas/odsaz/odsa-rotate-wallet.html','https://docs.oracle.com/iaas/odsaz/odsa-change-password.html','https://docs.oracle.com/iaas/odsaz/odsa-database-actions.html',]
+# Cache the loaded documents (outside any function)
+@st.cache_data
+def load_documents():
+    docs = UnstructuredURLLoader(urls=testurls).load()
+    print("Loading data")
+    print(docs)
+    return docs  # Return the loaded documents
+docs = load_documents()
+vectorstore = Qdrant.from_documents(docs, embeddings, location=":memory:", prefer_grpc=False, collection_name="test_db")
+retriever = vectorstore.as_retriever()
+rag_prompt_template = """Answer the question based only on the following context:
+{context}
+Question: {question}"""
+rag_prompt = PromptTemplate.from_template(rag_prompt_template)
+llm = OCIGenAI(
+    model_id="cohere.command",
+    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
+    compartment_id=compartment_id,
+    model_kwargs={"temperature": 0, "max_tokens": 300},
+)
+rag = RetrievalQA.from_chain_type(llm=llm, retriever=retriever, chain_type_kwargs={"prompt": rag_prompt})
+# Answer generation when a question is asked
+if st.button("Get Answer"):
+    question = st.session_state.question
+    # Ensure correct access to cached documents
+    docs = load_documents()  # Call the cached function to retrieve documents
+    data = rag.invoke(question, context=docs)  # Pass documents as context
+    answer = data["result"]
+    st.write("Answer:", answer)

ai-and-app-modernisation/ai-services/generative-ai-service/summarize-genai/files/requirements.txt

@@ -2,4 +2,5 @@ streamlit
 langchain
 unstructured
 langchain_community
-pypdf
+pypdf
+transformers