Marcus Schiesser
@MarcusSchiesser
Loves building LLM apps. Tech enthusiast and nature lover.
ID:1546053425552670720
http://www.marcusschiesser.de 10-07-2022 08:48:06
74 Tweets
421 Followers
201 Following
Did you know you can use local ollama models with `create-llama` from LlamaIndex 🦙?
You can add the `--ask-models` parameter and select, for example, AI at Meta's Llama3 or Microsoft's Phi-3 model.
Use `npx create-llama` to quickly create RAG applications using LlamaIndex 🦙.
Now, you can show the sources of the retrieved context (think of Perplexity). Watch the video below to see the feature in action.
📃 Code: github.com/run-llama/crea…
Introducing create-tsi - a toolkit to generate a full-stack, enterprise-grade (GDPR compliant) AI Application through a CLI interface! 🇪🇺🛠️🤖
This was done in collaboration with T-Systems, Marcus Schiesser, and inspired by the LlamaIndex 🦙 create-llama toolkit.
Build a…
Version 0.0.32 of `npx create-llama` from LlamaIndex 🦙 has many new features; it’s worth checking the changelog.
The video below shows how to create a TypeScript agent using a Wikipedia tool.
📋 Changelog: github.com/run-llama/crea…
🛠️ Code: github.com/run-llama/crea…
The course uses LlamaIndex 🦙's TypeScript library (npmjs.com/package/llamai…) which has been growing rapidly in popularity in the last few months and also in feature set thanks to Emanuel Ferreira and Marcus Schiesser who add new stuff every time I blink.
LlamaParse from LlamaIndex 🦙 helps LLMs to better understand documents by parsing them efficiently.
You can now use it in `npx create-llama` for your TS and Python projects.
`npx create-llama` lets you quickly generate LLM apps using LlamaIndex 🦙.
Did you know you can open a generated project directly in VS Code?
The video shows generating a FastAPI endpoint and opening it in a dev container.
Code 🛠️: github.com/run-llama/crea…
The new LlamaParse service from LlamaIndex 🦙 unlocks RAG over complex PDFs with embedded tables and charts.
To use it from LlamaIndexTS, you can use the `LlamaParseReader` as shown below.
Docs: ts.llamaindex.ai/modules/data_l…
Example: github.com/run-llama/Llam…
Use create-llama from LlamaIndex 🦙 to build an AI agent in seconds. Here's an example using the Wikipedia tool from LlamaHub.
Try it yourself using `npx create-llama@latest`.