src/genai/analytics_chatbot/utils/utils.py

import requests
import json
import re

def generate_api_knowledge(base_url: str):
    """
    Fetches FastAPI OpenAPI docs and summarizes endpoints, methods, parameters, and descriptions.
    Returns a JSON-friendly Python list of dicts, excluding the root endpoint.
    """
    resp = requests.get(f"{base_url}/openapi.json")
    resp.raise_for_status()
    spec = resp.json()

    api_knowledge = []

    for path, methods in spec["paths"].items():
        if path == "/":  # skip root endpoint
            continue

        for method, details in methods.items():
            endpoint = path
            description = details.get("description", "No description provided").strip()

            # collect parameters
            params = []
            for param in details.get("parameters", []):
                params.append(param.get("name"))

            # requestBody can also have parameters
            if "requestBody" in details:
                try:
                    body_schema = (
                        details["requestBody"]["content"]["application/json"]["schema"]
                    )
                    if "properties" in body_schema:
                        params.extend(body_schema["properties"].keys())
                except Exception:
                    pass

            api_knowledge.append({
                "endpoint": endpoint,
                "method": method.upper(),   
                "parameters": params,
                "description": description
            })

    return api_knowledge

def influencers_name():
    return {
  "information_of_influencers_usernames": "From the names_dictionary, the key represents their original names and the value represents their usernames (influencer_username).",
  "names_dictionary": {
    "divya dhakal": "divyadhakal_",
    "istu karki": "ishtukarkee",
    "kano mama": "kano_mama",
    "muna chiya": "munachiya",
    "nepal food": "nepal_food",
    "ggkaam": "ggkaam610",
    "adarsh": "adars_fpv",
    "ajay tamang": "ajaytm43",
    "anisha kafle": "anishakafle",
    "diwash gurung": "diwasg",
    "eat grub food": "eatgrubfood",
    "surakshya kc": "imsurakshyakc",
    "jholey": "jholeyism",
    "mrb vlogs": "mrbvlog2"
  }
}

def process_query(user_query: str) -> str:
    # load mapping from json file
    with open("src/genai/analytics_chatbot/utils/name_variations.json", "r") as f:
        variations = json.load(f)

    processed = user_query

    # Build reverse mapping: variation → username
    expanded = {}
    for username, names in variations.items():
        for n in names:
            expanded[n.lower()] = username

    # Replace names in query
    for name in sorted(expanded.keys(), key=len, reverse=True):
        pattern = r"\b" + re.escape(name) + r"\b"
        processed = re.sub(pattern, expanded[name], processed, flags=re.IGNORECASE)

    return processed