arthrod

Repository Overview

Directory Structure

pydantic-ai
├── LICENSE
├── Makefile
├── README.md
├── docs
│   ├── _worker.js

arthrod

import polars as pl
from datasets import load_from_disk

ds = load_from_disk("/home/arthrod/finlandia/form-d-a/edgar_filings/train/")

arrow_table = ds.data.table

lazy_df = pl.from_arrow(arrow_table)

filtered_lazy = lazy_df.filter(pl.col("form").eq("D/A")).limit(1000)

arthrod

Claude MCP Configuration Solutions

This gist documents two working approaches for Model Context Protocol (MCP) server configurations in Claude Desktop environments.

Solution 1: Shell Script Method

This approach uses a shell script to execute commands and works in Claude Desktop and Cursor.

Configuration in claude_desktop_config.json:

arthrod

#!/usr/bin/env python3
# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "typer",
#     "rich",
# ]
# ///
"""
JSONL Processor - A tool to modify JSONL files by adding or renaming keys, and merging multiple files.

arthrod

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "typer",
#     "datasets",
#     "loguru",
#     "google-genai",
#     "rich",
# ]
# ///

arthrod

LangGraph ReAct Agent – Comprehensive Guide

This document consolidates all core instructions and examples for using and extending LangGraph’s prebuilt ReAct agent. It covers the following topics, along with complete code examples (using triple backticks) and the names of the required packages:

• Using the Prebuilt ReAct Agent
• Adding Thread-Level Memory
• Adding a Custom System Prompt
• Returning Structured Output
• Adding Semantic Search to Your Agent’s Memory
• Running a Graph Asynchronously

arthrod

# #!/usr/bin/env -S uv run --script
# /// script
# dependencies = [
#   "pydantic-ai",
#   "python-dotenv",
#   "typer",
#   "rich",
# ]
# ///

arthrod

# https://docs.litellm.ai/docs/proxy/configs
# https://docs.litellm.ai/docs/proxy/quickstart

model_list:
  # https://docs.lambdalabs.com/public-cloud/lambda-inference-api/#listing-models
  - model_name: hermes3-70b
    litellm_params:
      model: openai/hermes3-70b
      api_key: "os.environ/OPENAI_API_KEY"
      api_base: "os.environ/OPENAI_API_BASE"

arthrod

"""
Module for interacting with the model via the OpenRouter API.
"""

import toml
import asyncio
from loguru import logger
from openai import OpenAI
import requests

arthrod

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "typer",
#     "datasets",
#     "loguru",
#     "huggingface_hub",
#     "google-genai",
#     "aiofiles",
#     "rich",