|
import os |
|
import gradio as gr |
|
|
|
from openai import OpenAI |
|
|
|
from optillm.cot_reflection import cot_reflection |
|
from optillm.rto import round_trip_optimization |
|
from optillm.z3_solver import Z3SolverSystem |
|
from optillm.self_consistency import advanced_self_consistency_approach |
|
from optillm.rstar import RStar |
|
from optillm.plansearch import plansearch |
|
from optillm.leap import leap |
|
|
|
|
|
API_KEY = os.environ.get("OPENROUTER_API_KEY") |
|
|
|
def respond( |
|
message, |
|
history: list[tuple[str, str]], |
|
model, |
|
approach, |
|
system_message, |
|
max_tokens, |
|
temperature, |
|
top_p, |
|
): |
|
client = OpenAI(api_key=API_KEY, base_url="https://openrouter.ai/api/v1") |
|
|
|
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}) |
|
|
|
if approach == 'rto': |
|
final_response = round_trip_optimization(system_prompt, initial_query, client, model) |
|
elif approach == 'z3': |
|
z3_solver = Z3SolverSystem(system_prompt, client, model) |
|
final_response = z3_solver.process_query(initial_query) |
|
elif approach == "self_consistency": |
|
final_response = advanced_self_consistency_approach(system_prompt, initial_query, client, model) |
|
elif approach == "rstar": |
|
rstar = RStar(system_prompt, client, model) |
|
final_response = rstar.solve(initial_query) |
|
elif approach == "cot_reflection": |
|
final_response = cot_reflection(system_prompt, initial_query, client, model) |
|
elif approach == 'plansearch': |
|
final_response = plansearch(system_prompt, initial_query, client, model) |
|
elif approach == 'leap': |
|
final_response = leap(system_prompt, initial_query, client, model) |
|
|
|
return final_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.Dropdown( |
|
["nousresearch/hermes-3-llama-3.1-405b:free", "meta-llama/llama-3.1-8b-instruct:free", "qwen/qwen-2-7b-instruct:free", |
|
"google/gemma-2-9b-it:free", "mistralai/mistral-7b-instruct:free", ], |
|
value="nousresearch/hermes-3-llama-3.1-405b:free", label="Model", info="Choose the base model" |
|
), |
|
gr.Dropdown( |
|
["leap", "plansearch", "rstar", "cot_reflection", "rto", "self_consistency", "z3"], value="cot_reflection", label="Approach", info="Choose the approach" |
|
), |
|
gr.Textbox(value="", 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)", |
|
), |
|
], |
|
) |
|
|
|
if __name__ == "__main__": |
|
demo.launch() |
