Upload 8 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
+vector_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,91 @@
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+
+import gradio as gr
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import CharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_openai import ChatOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains.question_answering import load_qa_chain
+
+text_splitter = CharacterTextSplitter(
+    separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len
+)
+embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
+llm = ChatOpenAI(model="gpt-4-1106-preview", api_key=OPENAI_API_KEY)
+
+vectordb_path = "./vector_db"
+uploaded_files = ["./pdf/knowledgebase.pdf"]
+vectorstore = None
+
+
+def create_vectordb():
+    global vectorstore
+    
+    for file in uploaded_files:
+        loader = PyPDFLoader(file)
+        data = loader.load()
+        texts = text_splitter.split_documents(data)
+
+        if vectorstore is None:
+            vectorstore = Chroma.from_documents(
+                documents=texts,
+                embedding=embeddings,
+                persist_directory=os.path.join(vectordb_path),
+            )
+        else:
+            vectorstore.add_documents(texts)
+
+
+def rag_bot(query, chat_history):
+    print(f"Received query: {query}")
+
+    template = """Please answer to human's input based on context. If the input is not mentioned in context, output something like 'I don't know'.
+    Context: {context}
+    Human: {human_input}
+    Your Response as Chatbot:"""
+
+    prompt_s = PromptTemplate(
+        input_variables=["human_input", "context"], template=template
+    )
+
+    vectorstore = Chroma(
+        persist_directory=os.path.join(vectordb_path), embedding_function=embeddings
+    )
+
+    docs = vectorstore.similarity_search(query)
+
+    stuff_chain = load_qa_chain(llm, chain_type="stuff", prompt=prompt_s)
+
+    output = stuff_chain(
+        {"input_documents": docs, "human_input": query}, return_only_outputs=False
+    )
+
+    final_answer = output["output_text"]
+    print(f"Final Answer ---> {final_answer}")
+
+    return final_answer
+
+
+def chat(query, chat_history):
+    response = rag_bot(query, chat_history)
+    return response
+
+
+if __name__ == "__main__":
+    # create_vectordb()
+
+    chatbot = gr.Chatbot(avatar_images=["user.jpg", "bot.png"], height=600)
+    clear_but = gr.Button(value="Clear Chat")
+    demo = gr.ChatInterface(
+        fn=chat,
+        title="RAG Chatbot Prototype",
+        multimodal=False,
+        chatbot=chatbot,
+    )
+    demo.launch(debug=True, share=True)

vector_db/8a199d61-18fe-45a3-9a2c-fafc0783cc78/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18abd8c514282db82706e52b0a33ed659cd534e925a6f149deb7af9ce34bd8e
+size 6284000

vector_db/8a199d61-18fe-45a3-9a2c-fafc0783cc78/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effaa959ce2b30070fdafc2fe82096fc46e4ee7561b75920dd3ce43d09679b21
+size 100

vector_db/8a199d61-18fe-45a3-9a2c-fafc0783cc78/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65d7c29560358d84b96d1093011ba25fc1ba008e41867ed1d65c5fc2bf7f34a
+size 4000

vector_db/8a199d61-18fe-45a3-9a2c-fafc0783cc78/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
+size 0

vector_db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b649ee0abb2614aee92ad4a81b099ea91f995c54032ec392a4cf2c0e35493a0
+size 3260416