sglang/benchmark/react/bench_sglang.py

import argparse
import json
import time

import sglang as sgl
from sglang.test.test_utils import (
    add_common_sglang_args_and_parse,
    select_sglang_backend,
)
from sglang.utils import dump_state_text, read_jsonl


@sgl.function
def webthink(s, question, triplets):
    s += (
        """Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current situation, and Action can be three types:
(1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it will return some similar entities to search.
(2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
(3) Finish[answer], which returns the answer and finishes the task.
Here are some examples.
Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought 1: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action 1: Search[Colorado orogeny]
Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.
Thought 2: It does not mention the eastern sector. So I need to look up eastern sector.
Action 2: Lookup[eastern sector]
Observation 2: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.
Thought 3: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.
Action 3: Search[High Plains]
Observation 3: High Plains refers to one of two distinct land regions:
Thought 4: I need to instead search High Plains (United States).
Action 4: Search[High Plains (United States)]
Observation 4: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought 5: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action 5: Finish[1,800 to 7,000 ft]
Question: Musician and satirist Allie Goertz wrote a song about the "The Simpsons" character Milhouse, who Matt Groening named after who?
Thought 1: The question simplifies to "The Simpsons" character Milhouse is named after who. I only need to search Milhouse and find who it is named after.
Action 1: Search[Milhouse]
Observation 1: Milhouse Mussolini Van Houten is a recurring character in the Fox animated television series The Simpsons voiced by Pamela Hayden and created by Matt Groening.
Thought 2: The paragraph does not tell who Milhouse is named after, maybe I can look up "named after".
Action 2: Lookup[named after]
Observation 2: (Result 1 / 1) Milhouse was named after U.S. president Richard Nixon, whose middle name was Milhous.
Thought 3: Milhouse was named after U.S. president Richard Nixon, so the answer is Richard Nixon.
Action 3: Finish[Richard Nixon]
Question: Which documentary is about Finnish rock groups, Adam Clayton Powell or The Saimaa Gesture?
Thought 1: I need to search Adam Clayton Powell and The Saimaa Gesture, and find which documentary is about Finnish rock groups.
Action 1: Search[Adam Clayton Powell]
Observation 1: Could not find [Adam Clayton Powell]. Similar: ['Adam Clayton Powell III', 'Seventh Avenue (Manhattan)', 'Adam Clayton Powell Jr. State Office Building', 'Isabel Washington Powell', 'Adam Powell', 'Adam Clayton Powell (film)', 'Giancarlo Esposito'].
Thought 2: To find the documentary, I can search Adam Clayton Powell (film).
Action 2: Search[Adam Clayton Powell (film)]
Observation 2: Adam Clayton Powell is a 1989 American documentary film directed by Richard Kilberg.
The film is about the rise and fall of influential African-American politician Adam Clayton Powell Jr.[3][4] It was later aired as part of the PBS series The American Experience.
Thought 3: Adam Clayton Powell (film) is a documentary about an African-American politician, not Finnish rock groups. So the documentary about Finnish rock groups must instead be The Saimaa Gesture.
Action 3: Finish[The Saimaa Gesture]
Question: What profession does Nicholas Ray and Elia Kazan have in common?
Thought 1: I need to search Nicholas Ray and Elia Kazan, find their professions, then find the profession they have in common.
Action 1: Search[Nicholas Ray]
Observation 1: Nicholas Ray (born Raymond Nicholas Kienzle Jr., August 7, 1911 – June 16, 1979) was an American film director, screenwriter, and actor best known for the 1955 film Rebel Without a Cause.
Thought 2: Professions of Nicholas Ray are director, screenwriter, and actor. I need to search Elia Kazan next and find his professions.
Action 2: Search[Elia Kazan]
Observation 2: Elia Kazan was an American film and theatre director, producer, screenwriter and actor.
Thought 3: Professions of Elia Kazan are director, producer, screenwriter, and actor. So profession Nicholas Ray and Elia Kazan have in common is director, screenwriter, and actor.
Action 3: Finish[director, screenwriter, actor]
Question: Which magazine was started first Arthur's Magazine or First for Women?
Thought 1: I need to search Arthur's Magazine and First for Women, and find which was started first.
Action 1: Search[Arthur's Magazine]
Observation 1: Arthur's Magazine (1844-1846) was an American literary periodical published in Philadelphia in the 19th century.
Thought 2: Arthur's Magazine was started in 1844. I need to search First for Women next.
Action 2: Search[First for Women]
Observation 2: First for Women is a woman's magazine published by Bauer Media Group in the USA.[1] The magazine was started in 1989.
Thought 3: First for Women was started in 1989. 1844 (Arthur's Magazine) < 1989 (First for Women), so Arthur's Magazine was started first.
Action 3: Finish[Arthur's Magazine]
Question: Were Pavel Urysohn and Leonid Levin known for the same type of work?
Thought 1: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same.
Action 1: Search[Pavel Urysohn]
Observation 1: Pavel Samuilovich Urysohn (February 3, 1898 â August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory.
Thought 2: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work.
Action 2: Search[Leonid Levin]
Observation 2: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist.
Thought 3: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work.
Action 3: Finish[yes]
"""
        + question
    )
    for i in range(1, len(triplets) + 2):
        s += "Thought " + str(i) + ":"
        # NOTE: This is an implementation for replaying a given trace for benchmark purposes. It is not an actual ReAct agent implementation.
        ss = s.fork(1)
        ss[0] += sgl.gen(name="thought_action", max_tokens=200, stop="Observation")
        ss.join()
        # to verify the correctness of output, this should be collected
        # print(ss[0]["thought_action"])
        if i > len(triplets):
            break
        s += (
            triplets[i - 1]["thought"]
            + "\nAction "
            + str(i)
            + ":"
            + triplets[i - 1]["action"]
            + "\nObservation "
            + str(i)
            + ":"
            + triplets[i - 1]["observation"]
            + "\n"
        )


def main(args):
    lines = read_jsonl(args.data_path)[: args.num_questions]
    arguments = [{"question": k, "triplets": v} for l in lines for k, v in l.items()]

    # Select backend
    backend = select_sglang_backend(args)
    sgl.set_default_backend(backend)

    states = []
    tic = time.time()
    states = webthink.run_batch(
        arguments,
        temperature=0,
        num_threads=args.parallel,
        progress_bar=True,
    )
    latency = time.time() - tic

    # Compute accuracy
    print(f"Latency: {latency:.3f}")

    # Write results
    dump_state_text(f"tmp_output_{args.backend}.txt", states)

    with open(args.result_file, "a") as fout:
        value = {
            "task": "ReAct Agents",
            "backend": args.backend,
            "num_gpus": 1,
            "latency": round(latency, 3),
            "num_requests": len(arguments),
            "other": {
                "num_questions": args.num_questions,
                "parallel": args.parallel,
            },
        }
        fout.write(json.dumps(value) + "\n")


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--data-path", type=str, default="hotpotqa_100.jsonl")
    parser.add_argument("--num-questions", type=int, default=10)
    args = add_common_sglang_args_and_parse(parser)
    main(args)