Upload app.py

app.py

@@ -1,103 +1,63 @@
-"""## WEBSITE CHAT BOT"""
-
-%%capture
-!pip  install langchain
-!pip install bitsandbytes accelerate transformers
-!pip install sentence_transformers
-!pip install unstructured
-!pip install faiss-cpu
-
-!huggingface-cli login
-
-%%capture
-!pip install numpy==1.24.4
-
-%%capture
-pip install -U langchain-community
-
-from langchain.document_loaders import UnstructuredURLLoader
-
-URLs = [
-    "https://fullstackacademy.in/"
-]
-
-loaders=UnstructuredURLLoader(urls=URLs)
-
-data=loaders.load()
-
-# creating the chunks
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-
-text_chunks=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
-
-chunks=text_chunks.split_documents(data)
-
-len(chunks)
-
-# calling huggingfaceembeddings class
-from langchain.embeddings import HuggingFaceEmbeddings
-
-embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
-
-# calling faiss vector database from langchain
-from langchain.vectorstores import FAISS
-
-vectordatabase=FAISS.from_documents(chunks,embeddings)
-
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM,pipeline
-from langchain import HuggingFacePipeline
-
-model="google/flan-t5-large"
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-model1 = AutoModelForSeq2SeqLM.from_pretrained(model)
-pipe = pipeline("text2text-generation", model=model1, tokenizer=tokenizer)
-llm = HuggingFacePipeline(
-    pipeline = pipe,
-    model_kwargs={"temperature": 0, "max_length": 500},
-)
-
-from langchain.prompts import PromptTemplate
-
-template = """use the context to provide a concise answer and if you don't know just say don't now.
-{context}
-Question: {question}
-Helpful Answer:"""
-QA_CHAIN_PROMPT = PromptTemplate.from_template(template)
-
-from langchain.chains import RetrievalQA
-
-qa_chain = RetrievalQA.from_chain_type(
-    llm, retriever=vectordatabase.as_retriever(), chain_type="stuff",chain_type_kwargs={"prompt": QA_CHAIN_PROMPT}
-)
-
-question = "Who is the co-founder?"
-result = qa_chain({"query": question})
-result["result"]
-
-question = "What is the data science course duration?"
-result = qa_chain({"query": question})
-result["result"]
-
-%%capture
-pip install gradio
-
 import gradio as gr
+from huggingface_hub import InferenceClient
+
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
 
-def fetch(question, history):
-  result = qa_chain({"query": question})
-  return result["result"]
 
-gr.ChatInterface(
-    fetch,
-    chatbot=gr.Chatbot(height=300),
-    textbox=gr.Textbox(placeholder="Ask me a yes or no question", container=False, scale=7),
-    title="Yes Man",
-    description="Ask Yes Man any question",
-    theme="soft",
-    examples=["contact details", "data science bootcamp fee?", "placements info","MERN fee"],
-    cache_examples=True,
-    retry_btn=None,
-    undo_btn="Delete Previous",
-    clear_btn="Clear",
-).launch(share=True)
+if __name__ == "__main__":
+    demo.launch()