模型演示界面 从一个函数到一个可共享的应用程序

event: token
data: {"index":0,"text":"Label:"}

event: token
data: {"index":1,"text":" positive."}

event: done
data: {"label":"positive","score":1.0,"tokens":11}

{
  "error": {
    "code": "text_too_long",
    "message": "The text has 812 characters. The limit is 500.",
    "hint": "Shorten the text to 500 characters or fewer.",
    "request_id": "a8f3c2b435e3"
  }
}

tokens = min(capacity, tokens + refill_rate * seconds_since_last_request)
accept the request if tokens >= 1, then subtract 1

python3 code/main.py
npx tsx code/main.ts

python3 code/main.py --serve
npx tsx code/main.ts --serve

def classify(text):
    words = WORD_RE.findall(text.lower())
    positive = sum(1 for word in words if word in POSITIVE)
    negative = sum(1 for word in words if word in NEGATIVE)
    score = (positive - negative) / max(1, positive + negative)
    if score > 0:
        label = "positive"
    elif score < 0:
        label = "negative"
    else:
        label = "neutral"
    return {"label": label, "score": round(score, 3), "positive_cues": positive,
            "negative_cues": negative, "words": len(words)}


def generate(text):
    result = classify(text)
    reply = (
        f"Label: {result['label']}. Positive cues: {result['positive_cues']}. "
        f"Negative cues: {result['negative_cues']}. Words read: {result['words']}."
    )
    parts = reply.split(" ")
    yield parts[0]
    for part in parts[1:]:
        yield " " + part

class DemoError(Exception):
    def __init__(self, status, code, message, hint, headers=None):
        super().__init__(message)
        self.status = status
        self.code = code
        self.message = message
        self.hint = hint
        self.headers = dict(headers or {})


def validate_text(payload, max_chars=MAX_CHARS):
    if "text" not in payload:
        raise DemoError(422, "missing_text", 'The field "text" is missing.', 'Add a "text" field with your input.')
    text = payload["text"]
    if not isinstance(text, str):
        raise DemoError(422, "text_not_string", 'The field "text" is not a string.', "Send the input as a string.")
    text = text.strip()
    if not text:
        raise DemoError(422, "empty_text", "The text is empty.", "Type a sentence or pick an example.")
    if len(text) > max_chars:
        raise DemoError(422, "text_too_long", f"The text has {len(text)} characters. The limit is {max_chars}.",
                        f"Shorten the text to {max_chars} characters or fewer.")
    if CONTROL_RE.search(text):
        raise DemoError(422, "control_characters", "The text contains control characters.",
                        "Remove the hidden characters, then send the text again.")
    return text

class TokenBucket:
    def __init__(self, capacity, refill_per_second, now):
        if capacity < 1:
            raise ValueError("capacity must be at least 1")
        if refill_per_second <= 0:
            raise ValueError("refill_per_second must be positive")
        self.capacity = float(capacity)
        self.refill_per_second = float(refill_per_second)
        self.tokens = float(capacity)
        self.updated = now

    def take(self, now, cost=1.0):
        elapsed = max(0.0, now - self.updated)
        self.tokens = min(self.capacity, self.tokens + elapsed * self.refill_per_second)
        self.updated = now
        if self.tokens >= cost:
            self.tokens -= cost
            return 0.0
        return (cost - self.tokens) / self.refill_per_second

def sse_event(event, data):
    payload = json.dumps(data, separators=(",", ":"), ensure_ascii=False)
    return f"event: {event}\ndata: {payload}\n\n".encode("utf-8")


def stream_events(text, generate_fn=generate, delay=0.0, sleep=time.sleep):
    count = 0
    try:
        for token in generate_fn(text):
            yield sse_event("token", {"index": count, "text": token})
            count += 1
            if delay:
                sleep(delay)
    except Exception:
        yield sse_event("error", MODEL_ERROR)
        return
    result = classify(text)
    yield sse_event("done", {"label": result["label"], "score": result["score"], "tokens": count})

def do_POST(self):
    app = self.server.app
    request_id = uuid.uuid4().hex[:12]
    client_id = self.client_address[0]
    started = time.perf_counter()
    route = self.path if self.path in self.routes else "other"
    status, code, chars = 200, None, 0
    try:
        declared = self.headers.get("Content-Length")
        try:
            if route == "other":
                raise DemoError(404, "not_found", "This endpoint does not exist.",
                                "Send requests to /api/predict or /api/stream.")
            size = check_body_size(declared, app.config.max_body_bytes)
        except DemoError:
            self.drain(int(declared) if declared and declared.isdigit() else 0)
            raise
        try:
            body = self.rfile.read(size)
        except TimeoutError:
            self.close_connection = True
            raise DemoError(408, "request_timeout", "The request body did not arrive in time.",
                            "Send the request again with the full body.") from None
        app.admit(client_id, self.headers.get("Authorization"))
        text = app.read_text(self.headers.get("Content-Type"), body)
        chars = len(text)
        app.charge()
        if route == "/api/predict":
            self.send_json(200, predict(text), request_id)
        else:
            code = self.send_stream(text, request_id)
    except DemoError as err:
        status, code = err.status, err.code
        self.send_error_json(err, request_id)
    except TimeoutError:
        status, code = 408, "request_timeout"
        self.close_connection = True
    except Exception:
        status, code = 500, "internal_error"
        self.send_error_json(DemoError(500, "internal_error", "The server failed on this request.",
                                       "Try again. Quote the request id if you report the problem."), request_id)
    finally:
        latency_ms = (time.perf_counter() - started) * 1000
        app.log.record(request_id, route, client_id, status, chars, latency_ms, code)

const reader = response.body.getReader();
const decoder = new TextDecoder();
let buffer = "";
while (true) {
  const chunk = await reader.read();
  if (chunk.done) { break; }
  buffer += decoder.decode(chunk.value, { stream: true });
  let cut = buffer.indexOf("\n\n");
  while (cut >= 0) {
    const frame = parseFrame(buffer.slice(0, cut));
    buffer = buffer.slice(cut + 2);
    cut = buffer.indexOf("\n\n");
    if (frame.event === "token") { output.textContent += frame.data.text; }
  }
}

def csp_hash(source):
    digest = hashlib.sha256(source.encode("utf-8")).digest()
    return "'sha256-" + base64.b64encode(digest).decode("ascii") + "'"

for i in 1 2 3 4 5 6 7; do
  curl -s -o /dev/null -w '%{http_code} ' -X POST http://127.0.0.1:8000/api/predict \
    -H 'Content-Type: application/json' -d '{"text": "ok"}'
done

200 200 200 200 200 429 429

curl -s -X POST http://127.0.0.1:8000/api/predict \
  -H 'Content-Type: application/json' -d '{"text": ""}'

{"error": {"code": "empty_text", "message": "The text is empty.", "hint": "Type a sentence or pick an example.", "request_id": "e3e3599feaea"}}

curl -N -X POST http://127.0.0.1:8000/api/stream \
  -H 'Content-Type: application/json' -d '{"text": "The screen is bright."}'

export DEMO_ACCESS_TOKEN="$(python3 -c 'import secrets; print(secrets.token_urlsafe(24))')"
echo "$DEMO_ACCESS_TOKEN"
python3 code/main.py --serve
npx tsx code/main.ts --serve

python3 -m unittest discover -s code/tests -v

import os

import gradio as gr

from main import EXAMPLES, MAX_CHARS, DemoError, classify, generate, validate_text


def label_text(text):
    try:
        clean = validate_text({"text": text})
    except DemoError as err:
        raise gr.Error(f"{err.message} {err.hint}")
    label = classify(clean)["label"]
    reply = ""
    for token in generate(clean):
        reply += token
        yield reply, label


demo = gr.Interface(
    fn=label_text,
    inputs=gr.Textbox(label="Text to label", lines=5, max_length=MAX_CHARS),
    outputs=[gr.Textbox(label="Reply"), gr.Textbox(label="Label")],
    examples=list(EXAMPLES),
    flagging_mode="never",
)

if __name__ == "__main__":
    demo.queue(max_size=20).launch(auth=("demo", os.environ["DEMO_PASSWORD"]))

import streamlit as st

from main import EXAMPLES, MAX_CHARS, DemoError, classify, generate, validate_text

st.title("Toy sentiment demo")
st.caption("Do not paste private data.")

example = st.selectbox("Start from an example", ["", *EXAMPLES])
with st.form("demo"):
    text = st.text_area("Text to label", value=example, max_chars=MAX_CHARS)
    submitted = st.form_submit_button("Run model")

if submitted:
    try:
        clean = validate_text({"text": text})
    except DemoError as err:
        st.error(f"{err.message} {err.hint}")
    else:
        st.write_stream(generate(clean))
        st.write(f"Label: {classify(clean)['label']}")