Getting Slow Calls Off the Request Path

import json
from enum import Enum
from pydantic import BaseModel, Field, ValidationError
class Sentiment(str, Enum):
    POSITIVE = "positive"
    NEUTRAL = "neutral"
    NEGATIVE = "negative"
class FeedbackCategory(str, Enum):
    PRODUCT_QUALITY = "product_quality"
    CUSTOMER_SERVICE = "customer_service"
    PRICING = "pricing"
    OTHER = "other"
class Confidence(str, Enum):
    HIGH = "high"
    LOW = "low"
class Feedback(BaseModel):
    sentiment: Sentiment
    category: FeedbackCategory
    severity: int = Field(ge=1, le=5, default=1)
    confidence: Confidence
    summary: str
def build_feedback_prompt(feedback_text: str) -> str:
    return (
        "Analyze the customer feedback below. Respond with a JSON object "
        "in exactly this shape, and nothing else:\n\n"
        "{\n"
        '  "sentiment": <one of: "positive", "neutral", "negative">,\n'
        '  "category": <one of: "product_quality", "customer_service", '
        '"pricing", "other">,\n'
        '  "severity": <integer from 1 to 5>,\n'
        '  "confidence": <one of: "high", "low">,\n'
        '  "summary": <string, one short sentence>\n'
        "}\n\n"
        f'Feedback: "{feedback_text}"'
    )
def build_repair_prompt(original_prompt: str, bad_response: str, error: ValidationError) -> str:
    return (
        f"{original_prompt}\n\nYour previous response did not match the "
        f"required format. Previous response:\n{bad_response}\n\n"
        f"Validation error:\n{error}\n\nRespond again with only the "
        "corrected JSON object."
    )
def strip_code_fence(text: str) -> str:
    stripped = text.strip()
    if stripped.startswith("```"):
        lines = stripped.split("\n")[1:]
        if lines and lines[-1].strip() == "```":
            lines = lines[:-1]
        return "\n".join(lines).strip()
    return stripped
# USE_MOCK is True by default, so this file runs immediately with no
# API key. Set it to False and fill in a real provider block below to
# use an actual model.
USE_MOCK = True
def call_llm(prompt: str) -> str:
    if USE_MOCK:
        return (
            '{"sentiment": "negative", "category": "customer_service", '
            '"severity": 4, "confidence": "high", '
            '"summary": "Support took days to reply."}'
        )
    # from openai import OpenAI
    # client = OpenAI(api_key="your-openai-api-key")
    # response = client.chat.completions.create(
    #     model="your-chosen-openai-model",
    #     messages=[{"role": "user", "content": prompt}],
    # )
    # return response.choices[0].message.content
    raise NotImplementedError("Fill in a real provider block, or set USE_MOCK back to True.")
def get_validated_feedback(feedback_text: str, max_attempts: int = 2) -> Feedback:
    prompt = build_feedback_prompt(feedback_text)
    current_prompt = prompt
    for attempt in range(1, max_attempts + 1):
        raw_response = call_llm(current_prompt)
        cleaned = strip_code_fence(raw_response)
        try:
            parsed = json.loads(cleaned)
        except json.JSONDecodeError:
            continue
        try:
            return Feedback.model_validate(parsed)
        except ValidationError as error:
            current_prompt = build_repair_prompt(prompt, cleaned, error)
    return Feedback(
        sentiment=Sentiment.NEUTRAL,
        category=FeedbackCategory.OTHER,
        severity=3,
        confidence=Confidence.LOW,
        summary="Could not be automatically assessed.",
    )