Skip to content

Instantly share code, notes, and snippets.

View akashsharma95's full-sized avatar
🎯
Focusing

Akash Sharma akashsharma95

🎯
Focusing
View GitHub Profile
@jlia0
jlia0 / agent loop
Last active April 23, 2025 08:40
Manus tools and prompts
You are Manus, an AI agent created by the Manus team.
You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet
@willccbb
willccbb / grpo_demo.py
Last active April 22, 2025 19:16
GRPO Llama-1B
# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer
@dannguyen
dannguyen / README.openai-structured-output-demo.md
Last active April 14, 2025 16:56
A basic test of OpenAI's Structured Output feature against financial disclosure reports and a newspaper's police blotter. Code examples use the Python SDK and pydantic for the schema definition.

Extracting financial disclosure reports and police blotter narratives using OpenAI's Structured Output

tl;dr this demo shows how to call OpenAI's gpt-4o-mini model, provide it with URL of a screenshot of a document, and extract data that follows a schema you define. The results are pretty solid even with little effort in defining the data — and no effort doing data prep. OpenAI's API could be a cost-efficient tool for large scale data gathering projects involving public documents.

OpenAI announced Structured Outputs for its API, a feature that allows users to specify the fields and schema of extracted data, and guarantees that the JSON output will follow that specification.

For example, given a Congressional financial disclosure report, with assets defined in a table like this:

@veekaybee
veekaybee / normcore-llm.md
Last active April 20, 2025 11:25
Normcore LLM Reads

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Screenshot 2023-12-18 at 10 40 27 PM

Pre-Transformer Models

@amir734jj
amir734jj / confluent-interview-questions.txt
Last active March 24, 2025 18:35
confluent-interview-questions
Glassdoor questions:
- Given a game to you which is running on an instance and hasMySQL installed on it locally, now with the game popularity increasing, suggest ways that it stays highly secure and highly available and then with every step he was adding more things on it, like we want to use JWT on it, should we use it? session maintenance etc.
- URL shortener in Go
- MRU cache implementation in java or Go
- Distributed Systems, Coding Comprehension
- garbage collection in Java
- SFDC related experience
- debounce function
- Memory management for Java applications
@shathor
shathor / EjectingQueue.java
Last active October 14, 2021 19:26
Sliding window view on a stream / sequence of data. A non-blocking circular queue which automatically evicts elements from the head of the queue when attempting to add new elements into the array and it is full. Provides element insertion and removal at opposite ends (like a queue) and access to random elements in the container (like an array).
package ch.sgwerder.gist;
import java.lang.reflect.Array;
import java.util.Arrays;
import java.util.Collection;
import java.util.Iterator;
import java.util.RandomAccess;
/**
* Copyright (C) 2015 Simon Gwerder.
@akashsharma95
akashsharma95 / Simple Python Google Speech API
Last active December 16, 2015 23:59
Simple Python Google Speech API
The required modules and programs are :--
-libav
-python-requests
I have used libav here you can also use ffmpeg etc...