Personal AI Assistant: 'Ada' - v0.2
|
April 26, 2024, 6:37 a.m. |
Positional Periodic Table Embedding
|
April 25, 2024, 9:52 p.m. |
Auto choosing chunked ai summary bot
|
April 25, 2024, 8:31 p.m. |
llama3-8b-instruct 4bit quantize
|
April 25, 2024, 2:31 a.m. |
LLama index weave integration starter code
|
April 24, 2024, 11:54 p.m. |
Python script with a search with openai chat of how many albums does taylor swift have x with rag with the same chat
|
April 24, 2024, 10:40 p.m. |
ChatGPT-generated script to change portal data status based on data present (not tested yet)
|
April 24, 2024, 8 p.m. |
Python script introduction to langchain using openai, prompt template and chain
|
April 24, 2024, 7:55 p.m. |
LLM inference on modal labs through vLLM engine. This gives an endpoint which is OpenAI python client compatible.
|
April 24, 2024, 7:11 p.m. |
Get file structure for LLM upload
|
April 24, 2024, 1:23 p.m. |
Groq API chatbot using Llama3
|
April 24, 2024, 10:37 a.m. |
repair malformed bidi strings and add to an isolated embedding.
|
April 24, 2024, 8:33 a.m. |
Basic Groq API Response Streaming using Llama3
|
April 24, 2024, 7:36 a.m. |
Basic Groq API Response Streaming using Llama3
|
April 24, 2024, 7:27 a.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 24, 2024, 1:58 a.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 24, 2024, 1:24 a.m. |
llama-index vector store migration script from embedded json-based one to another one
|
April 24, 2024, 12:11 a.m. |
Personal AI Assistant: 'Ada' - v0.2
|
April 23, 2024, 9:18 p.m. |
Personal AI Assistant: 'Ada' - v0
|
April 23, 2024, 9:16 p.m. |
LLama 3 - Local Deployment
|
April 23, 2024, 4:34 p.m. |
Personal AI Assistant: 'Ada' - v0.2
|
April 23, 2024, 4:28 p.m. |
Guardrails AI Streaming PII Validation
|
April 23, 2024, 3:40 p.m. |
speech to text to speech using Ollama
|
April 23, 2024, 10:15 a.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 23, 2024, 2:02 a.m. |
Personal AI Assistant: 'Ada' - v0
|
April 23, 2024, 12:59 a.m. |
Ollama call with basic params
|
April 22, 2024, 7:16 p.m. |
A simple LLM Application that takes product name as input and generates a short description about the product and later scraps images related to same using web.
|
April 22, 2024, 6:12 p.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 22, 2024, 4:25 p.m. |
Personal AI Assistant: 'Ada' - v0.2
|
April 22, 2024, 4:22 p.m. |
Personal AI Assistant: 'Ada' - v0.2
|
April 22, 2024, 3:51 p.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 22, 2024, 3:35 p.m. |
exllama minimum example
|
April 22, 2024, 9:05 a.m. |
Use these Prompt Chains to build HIGH QUALITY AI Agents (Agentic Building Blocks)
|
April 22, 2024, 7:01 a.m. |
Run Llama 3 8B with Llamafile
|
April 22, 2024, 2:54 a.m. |
Python use the OpenAI with a local LLM (Using Ollama)
|
April 22, 2024, 12:49 a.m. |
Stupid-ass histogram equalization and target detection/tracking that I mashed together using AI and my stupid prior openCV knowledge
|
April 21, 2024, 11:12 p.m. |
A simple LLM Application that takes product name as input and generates a short description about the product and later scraps images related to same using web.
|
April 21, 2024, 9:46 p.m. |
Create LLM slices at runtime with exllamav2
|
Jan. 12, 2024, 6:57 p.m. |
Automatically detect song/video title/artist/album/metadata captured in screenshots using GPT-4-vision via the OpenAI API.
|
Jan. 12, 2024, 2:43 p.m. |
Jarvis AI copilot/assistant
|
Jan. 12, 2024, 1:16 p.m. |
Connect Four game class with an AI that uses the minimax algorithm. Playable in the terminal.
|
Jan. 12, 2024, 11:32 a.m. |
Quick “hello world” style ChatBot based on Ollama running locally
|
Jan. 12, 2024, 9:26 a.m. |
Configure azure openai with data from .env file
|
Jan. 12, 2024, 8:10 a.m. |
translate code from one language to another with chatgpt
|
Jan. 11, 2024, 3:42 p.m. |
Streamlit chatbot connected to MemGPT (OpenAI Back end)
|
Jan. 10, 2024, 5:50 p.m. |
Program using OpenAI's assistant API to solve math problems.
|
Jan. 10, 2024, 3:20 p.m. |
openai-fine-tuning-estimate-cost.py
|
Jan. 10, 2024, 2:02 p.m. |
proxy openai request with copilot
|
Jan. 10, 2024, 11:12 a.m. |
OpenAI GPT Vision Token Counting
|
Jan. 10, 2024, 8:06 a.m. |
QA Chatbot streaming with source documents example using FastAPI, LangChain Expression Language, OpenAI, and Chroma.
|
Jan. 10, 2024, 3:57 a.m. |
ad2 generates a query engine. Loader downloads and indexes Guru cards from a collection. Requires llama_index and chromadb.
|
Jan. 9, 2024, 9 p.m. |
OPENAI
|
Jan. 9, 2024, 7:07 p.m. |
embedding a plotly
|
Jan. 9, 2024, 1:36 p.m. |
Embedding Plot into Medium
|
Jan. 9, 2024, 12:56 p.m. |
Embedding a plotly with gist
|
Jan. 9, 2024, 12:56 p.m. |
Llamaindex chat with docs
|
Jan. 8, 2024, 4:40 p.m. |
meta ai research - segment anything example
|
Jan. 8, 2024, 6:41 a.m. |
python, aws, bedrock, llama2 model
|
Jan. 8, 2024, 5:11 a.m. |
custom gpts
|
Jan. 8, 2024, 2:38 a.m. |
MediumBlogging-Vertex AI custom container deployment-prediction_input.py
|
Jan. 8, 2024, 12:01 a.m. |
MediumBlogging-Vertex AI custom container deployment-obslib.py
|
Jan. 7, 2024, 11:59 p.m. |
MediumBlogging-Vertex AI custom container deployment-app.py
|
Jan. 7, 2024, 11:58 p.m. |
A python class then implements RAG using Open AI assistant API
|
Jan. 7, 2024, 10:33 p.m. |
Train a GPT to write like Shakespeare
|
Jan. 7, 2024, 4:47 p.m. |
llama-cpp-mistral-chat-format
|
Jan. 7, 2024, 12:55 p.m. |
ollama python utility script
|
Jan. 7, 2024, 12:28 a.m. |
Combining XTTS speaker embeddings
|
Jan. 6, 2024, 2:58 a.m. |
Скрипт для работы с chadgpt.ru, позволяет из консоли обращаться к боту
|
Jan. 5, 2024, 3:34 p.m. |
ChatGPT can analyze the secret message from the GEMINI demo with a few hints from the user (https://developers.googleblog.com/2023/12/how-its-made-gemini-multimodal-prompting.html)
|
Jan. 5, 2024, 12:40 p.m. |
An example implementation of HyDE embeddings with Haystack 2.0
|
Jan. 5, 2024, 12:24 p.m. |
Use Ollama with a local LLM to query websites
|
Jan. 5, 2024, 12:12 a.m. |
Query web pages with local LLMs using Ollama and Langchain
|
Jan. 4, 2024, 6:53 p.m. |
capped parallel requests to openai
|
Jan. 4, 2024, 5:20 p.m. |
python chatgpt
|
Jan. 4, 2024, 3:14 p.m. |
Script to send a PDF file to ChatGPT page by page
|
Jan. 4, 2024, 5:25 a.m. |
Plan a query with OpenAI function calls
|
Jan. 4, 2024, 4:36 a.m. |
Azure OpenAI On Your Data pre-GA API Example
|
Jan. 3, 2024, 9:36 p.m. |
Shows a little panel to mute shape keys matching a specific filter. Mutes all if no filter set. Made with the help of ChatGPT because my Python sucks!
|
Jan. 3, 2024, 3:49 p.m. |
SARSA implementation for the OpenAI gym Frozen Lake environment
|
Jan. 2, 2024, 8:58 p.m. |
Cutting up a llama and putting it back together
|
Jan. 2, 2024, 4:14 p.m. |
Using LangChain, OpenAI, and Summarize chains to create JSON objects that can be loaded using GenAnki to create Anki Flashcards
|
Jan. 2, 2024, 12:04 p.m. |
How to use Keymate.AI Python API as part of OpenAI Function calling
|
Jan. 2, 2024, 9:32 a.m. |
Example of using OpenAI functions in completions with Python decorators.
|
Jan. 1, 2024, 11:19 a.m. |
CLI based embedding search using OpenAI
|
Jan. 1, 2024, 11:18 a.m. |
Easy Llama 2 fine-tuning script (📝 Article: https://tinyurl.com/finetunellama2)
|
Jan. 1, 2024, 12:07 a.m. |
Willow Speech + Local LLM + HomeAssistant
|
Dec. 31, 2023, 3:24 p.m. |
Convert markdown issue, PR, commit references to GitHub links (written by ChatGPT)
|
Dec. 31, 2023, 10:48 a.m. |
Talking AI Assistant Application on Streamlit
|
Dec. 31, 2023, 4:25 a.m. |
EchoFuck by ChatGPT (faulty)
|
Dec. 30, 2023, 10:40 p.m. |
Brainfuck in Python generated by ChatGPT
|
Dec. 30, 2023, 10:29 p.m. |
LlamaCPP sample- GRDN.AI
|
Dec. 30, 2023, 6:59 p.m. |
Script to decompose/recompose LLAMA LLM models with different number of shards.
|
Dec. 30, 2023, 5:09 p.m. |
Easy Llama 2 fine-tuning script (📝 Article: https://tinyurl.com/finetunellama2)
|
Dec. 30, 2023, 4:04 p.m. |
watashiha-gpt-6bのgguf変換コード byteのtokenが無いので使ってなさそうな絵文字の一部をbyteトークンに再割り当てして対応
|
Dec. 29, 2023, 6:14 p.m. |
Use Imagen models on Vertex AI for image generation and captioning
|
Dec. 29, 2023, 4:27 p.m. |
Simple trading environment using openai gym
|
Dec. 29, 2023, 8:25 a.m. |
OpenAI Skeleton for Those Looking to Iteratively Employ ChatGPT
|
Dec. 29, 2023, 5:08 a.m. |
AutoGen + MemGPT Setup
|
Dec. 29, 2023, 1:47 a.m. |
Ejemplo de uso del API de ChatGPT desde Python
|
Dec. 29, 2023, 1:25 a.m. |
GPT-based categorization of JIRA issues
|
Dec. 28, 2023, 4:39 p.m. |