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?"}])

Mockapapella

# Writing Code and Documentation

## ⚠️ CRITICAL: ALL CODE MUST BE IN ARTIFACTS ⚠️
The single most important rule: NEVER write code directly in the conversation. ALL code MUST be provided as a unified diff file within an artifact. No exceptions.

## Before You Start
1. Read the user's request
2. Plan your response
3. Create a SINGLE unified diff file containing ALL code changes
4. Place this diff file in an artifact

othyn

Setting up a local only LLM (Qwen/Llama3/etc.) on macOS with Ollama, Continue and VSCode

As with a lot of organisations, the idea of using LLM's is a reasonably frightning concept, as people freely hand over internal IP and sensitive comms to remote entities that are heavily data bound by nature. I know it was on our minds when deciding on LLM's and their role within the team and wider company. 6 months ago, I set out to explore what offerings were like in the self-hosted and/or OSS space, and if anything could be achieved locally. After using this setup since then, and after getting a lot of questions on it, I thought I might share some of the things I've come across and getting it all setup.

Que in Ollama and Continue. Ollama is an easy way to locally download, manage and run models. Its very familiar to Docker in its usuage, and can probably be most conceptually aligned with it in how it operates, think imag

archydeberker

from typing import List
from uuid import UUID
from sqlalchemy import create_engine
from sqlalchemy.orm import Session, sessionmaker
from fastapi import FastAPI, Depends, HTTPException
from sqlalchemy.orm import Session
from pydantic import BaseModel

class User(BaseModel):
    # This is a DB model - in SQLModel you can return the ORM model directly bc it's Pydantic under the hood

virattt

timothywarner

🚀 GitHub Copilot Certification Resources

🔗 Short link to this gist: timw.info/copilotreview

🎥 Associated YouTube video: timw.info/8dc

📬 Contact information

• 📧 Tim Warner
• 🐙 GitHub: Personal and Organization

s3rgeym

from __future__ import annotations
from datetime import datetime
from typing import Any, Dict, List, Optional, AsyncGenerator
from sqlalchemy.dialects.postgresql import TIMESTAMP
from fastapi import Depends, FastAPI, Request
from fastapi.exceptions import RequestValidationError
from fastapi.responses import JSONResponse
from pydantic import BaseModel, Field, ValidationError, validator
from pydantic_settings import BaseSettings
from sqlalchemy import JSON, Column, DateTime, Integer, String, func

otmb

# https://www.starlette.io/requests/
# https://developer.mozilla.org/ja/docs/Web/API/Streams_API/Using_readable_streams
from fastapi import FastAPI, Request, HTTPException
from fastapi.responses import HTMLResponse, StreamingResponse, Response
from logging import getLogger, StreamHandler
import asyncio
import tempfile
import json
import time
import os

shresthakamal

"""CORS or "Cross-Origin Resource Sharing" refers to the situations when a frontend running in a browser has JavaScript code that communicates with a backend, and the backend is in a different "origin" than the frontend.



Origin
An origin is the combination of protocol (http, https), domain (myapp.com, localhost, localhost.tiangolo.com), and port (80, 443, 8080).

So, all these are different origins:

http://localhost

itsfrank

-- add 2 commands:
--    CodeCompanionSave [space delimited args]
--    CodeCompanionLoad
-- Save will save current chat in a md file named 'space-delimited-args.md'
-- Load will use a telescope filepicker to open a previously saved chat

-- create a folder to store our chats
local Path = require("plenary.path")
local data_path = vim.fn.stdpath("data")
local save_folder = Path:new(data_path, "cc_saves")