aravindkarnam

#r "Newtonsoft.Json"
#r "Microsoft.Rest.ClientRuntime.dll"
#r "Microsoft.Bot.Connector.Utilities.dll"
#r "Microsoft.Bot.Connector.dll"
using System.Net;  
using Microsoft.Bot.Connector;

public static async Task<HttpResponseMessage> Run(HttpRequestMessage req, TraceWriter log)
{   
    log.Verbose($"C# HTTP trigger function processed a request. RequestUri={req.RequestUri}");

aravindkarnam

#--------------------------
# USER-SPECIFIED DATA
#--------------------------

# Tune these parameters

num_classes = 2
image_shape = (160, 576)
EPOCHS = 40
BATCH_SIZE = 16

aravindkarnam

import asyncio
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai import AsyncWebCrawler, CacheMode, CrawlerRunConfig, BrowserConfig
import json
import os
from playwright.async_api import Page, BrowserContext

async def before_retrieve_html(page: Page, context: BrowserContext, **kwargs):
        # Called before final HTML retrieval.
        print("[HOOK] before_retrieve_html - We can do final actions")

aravindkarnam

import asyncio
import json
from crawl4ai import (
    AsyncWebCrawler,
    CacheMode,
    CrawlerRunConfig,
    LLMConfig,
    JsonCssExtractionStrategy,
)
import time

aravindkarnam

import asyncio
import json
from pprint import pprint
from crawl4ai import (
    AsyncWebCrawler,
    CrawlerRunConfig,
    BrowserConfig,
    JsonCssExtractionStrategy,
    LLMConfig,
)

aravindkarnam

from crawl4ai import (
    CrawlerRunConfig,
    BrowserConfig,
    AsyncWebCrawler,
    JsonCssExtractionStrategy,
    LLMConfig,
)
from crawl4ai.utils import preprocess_html_for_schema
import asyncio

aravindkarnam

from crawl4ai import (
    CrawlerRunConfig,
    BrowserConfig,
    AsyncWebCrawler,
    DefaultMarkdownGenerator,
    BM25ContentFilter,
)
import asyncio
from pprint import pprint