rajivmehtaflex

#uv add browser-use
#playwright install-dep
#playwright install-deps
#playwright install

import asyncio
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from browser_use.browser.browser import Browser, BrowserConfig
from browser_use import Agent

rajivmehtaflex

model: mistral:mistral-small-latest
clients:
- type: gemini
  api_key: <KEY>
- type: openai
  api_key: <KEY>
- type: openai-compatible
  name: mistral
  api_base: https://api.mistral.ai/v1
  api_key: <KEY>

rajivmehtaflex

#!/bin/bash

# Set errexit to exit immediately if a command exits with a non-zero status
set -e

# Print a message indicating the start of the script
echo "Starting Rust installation script..."

# Download and execute the rustup installer
echo "Downloading and executing rustup installer..."

rajivmehtaflex

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

rajivmehtaflex

import asyncio
import base64
import json
import os
import pyaudio
from websockets.asyncio.client import connect


class SimpleGeminiVoice:
    def __init__(self):

rajivmehtaflex

File: gemini_thinking_deep.py

from google import genai
import os
os.environ['GEMINI_API_KEY'] = '<KEY>'

client = genai.Client(
    api_key=os.environ['GEMINI_API_KEY'],
    http_options={

rajivmehtaflex

Custom Context Provider for Continue.dev VS Code Extension

This gist demonstrates how to create a custom context provider for the Continue.dev VS Code extension using a FastAPI server. This allows you to integrate external data sources or custom logic into the Continue.dev context.

Overview

The provided code consists of two files:

1. server.py: A Python file that sets up a FastAPI server with a single endpoint /check. This endpoint receives data in the form of a JSON object, and returns a JSON response with content and description.
2. requirements.txt: A text file that lists the Python dependencies required to run the FastAPI server.

rajivmehtaflex

Setting Python 3.12 as Default on macOS Sequoia 15.2

This guide explains how to set Python 3.12 as the default Python version on macOS Sequoia 15.2, so that typing python in the terminal runs Python 3.12. It also covers keeping the ability to call any Python 3.x version using python3.

Understanding the Situation

• macOS System Python: macOS has a system Python installation at /usr/bin/python, used by the OS and should not be modified.
• Multiple Python Versions: You likely have multiple Python versions installed, possibly via Homebrew.
• python vs. python3: Typically, python points to an older version, while python3 specifically calls Python 3. The goal is to have python point to 3.12 while still being able to use python3 for other 3.x versions.

rajivmehtaflex

Aider-Composer Setup Guide

Prerequisites

Before you start, ensure you have installed the Aider-Composer extension from the Visual Studio Code Marketplace:

• Install Aider-Composer from VSCode Marketplace

Setup Commands

rajivmehtaflex

from langchain_openai import ChatOpenAI

model=ChatOpenAI(
	temperature=0.5,
	model='codellama/CodeLlama-34b-Instruct-hf',
	base_url='https://api-inference.huggingface.co/v1/',
	api_key='<KEY>'
)

response=model.invoke(input=[{"role": "user", "content": "What is color of flamingo?"}])