bizrockman

import os
from openai import OpenAI
import json
import re
import hashlib
import random
from tqdm import tqdm
from dotenv import load_dotenv

load_dotenv()

bizrockman

from appwrite.client import Client
from dotenv import load_dotenv

def init_appwrite_client() -> Client:
    '''
    Init Appwrite client and return Databases object
    '''
    client = Client()
    client.set_endpoint(os.getenv("APPWRITE_ENDPOINT"))
    client.set_project(os.getenv("APPWRITE_PROJECT_ID"))

bizrockman

from appwrite.client import Client
from appwrite.services.databases import Databases
from appwrite.services.storage import Storage
from appwrite.query import Query

...
app_database = Databases(appwrite_client)

result = database.list_documents(
            database_id=database_id,

bizrockman

{
  "openapi": "3.0.0",
  "info": {
    "title": "Context7 API",
    "version": "1.0.0",
    "description": "LLM-optimized interface for accessing Context7 developer documentation."
  },
  "servers": [
    {
      "url": "https://context7.com/api/v1"

bizrockman

import json
import os
import re
from typing import Any, Optional

import litellm
from litellm import completion, completion_cost
from litellm.caching.caching import Cache
from litellm.main import ModelResponse, Usage
from loguru import logger

bizrockman

#!/usr/bin/env python3
"""
tau2_summarizer.py
------------------
Summarize Tau²-Bench result files (JSON) for Dual-Control, Retail runs.

- Reads a Tau² result JSON (created via `--save-to ...`)
- Aggregates per-task token usage and durations
- Computes Pass@1, totals, and normalized "per interaction" metrics (Dual = 2 * tasks)
- Optionally computes costs if prices are provided (USD per 1M tokens for input/output)

bizrockman

import json
import os
import re
from typing import Any, Optional

import litellm
from litellm import completion, completion_cost
from litellm.caching.caching import Cache
from litellm.main import ModelResponse, Usage
from loguru import logger