from huggingface_hub import InferenceClient
import gradio as gr
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vector_store = FAISS.load_local("TaoGPT-Embeddings", embeddings)
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.1"
)
NOMIC = """
TaoGPT - DataMap
"""
RAG = True
def format_prompt(message, history):
global RAG
if RAG == True:
results = vector_store.similarity_search(message ,k=3)
context = [result.page_content for result in results]
context = "\n\n".join(context)
print(context)
prompt = ""
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response} "
prompt += f"[INST]Given the following Information:\n{context} \n answer the following question {message} [/INST]"
return prompt
else:
prompt = ""
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response} "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(prompt, history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
]
css = """
#mkd {
height: 500px;
overflow: auto;
border: 1px solid #ccc;
}
"""
with gr.Blocks(css=css) as demo:
# gr.HTML("Mistral 7B Instruct")
# gr.HTML("In this demo, you can chat with Mistral-7B-Instruct model. 💬")
# gr.HTML("Learn more about the model here. 📚")
gr.HTML("TaoGPT
")
gr.HTML("TaoGPT is Fine-tuned Mistal-7B model on TaoScience related Information Check out- Github Repo For More Information. 💬")
with gr.Row():
with gr.Column():
gr.HTML("Chat with TaoGPT
")
gr.ChatInterface(
generate,
additional_inputs=additional_inputs,
examples=[["What is TaoScience"], ["Give me a Summary about TaoScience"]]
)
RAG_Checkbox = gr.Checkbox(label="Use Retrival Augmented Generation" , value=True , interactive=False)
with gr.Column():
gr.HTML("Look into the Dataset we used to Finetune our Model
")
gr.HTML(NOMIC)
demo.queue(concurrency_count=75, max_size=100).launch(debug=True)