. The author experiments with the model, asking it to add a walrus to a prompt, and is surprised to find that the model can maintain consistency between images with a slightly altered prompt using a "seed" number. The author also delves into the underlying prompt engineering of DALL-E 3, revealing policies and guidelines that govern the model's image generation, including diversity and inclusivity guidelines.
* **GPT4All**: A desktop application that allows you to run large language models (LLMs) locally, with a simple setup and a clean chat interface.
* **LLM**: A command-line tool that enables you to download and use open-source LLMs locally, with plugins for various models, including GPT4All and Meta's Llama.
* **Ollama**: A simple, point-and-click installation process for running Llama models on your desktop, with a user-friendly interface for chatting with your own documents.
* **h2oGPT**: A desktop application that allows you to chat with your own documents using natural language and get a generative AI response, with a basic version available for download.
* **PrivateGPT**: A tool that enables you to query your own documents using natural language and get a generative AI response, with a simplified version available for non-experts.
* **Jan**: An open-source project that offers a simple interface for chatting with local models, with the ability to upload files and chat with documents (although with some limitations).
* **Opera**: A convenient, but potentially less private, way to chat with local models using the developer version of Opera, with some limitations.
* **Chat with RTX**: A simple interface for answering questions about a directory of documents using Llama 2 LLM, with some limitations and requirements (e.g., Nvidia GeForce RTX 30 Series or higher GPU).
* **llamafile**: A tool that allows developers to turn critical portions of large language models into executable files, with a simple setup process, but some limitations (e.g., currently not ideal for Windows).
* **LocalGPT**: A spinoff of PrivateGPT with more model options and detailed instructions, but with a warning that running on a CPU alone will be slow.
* **LM Studio**: A desktop app with a clean interface for running chats, but requires knowledge of model selection and has some limitations (e.g., no built-in option for running LLM over your own data).
* **LangChain**: A framework for creating end-to-end generative AI applications, requiring knowledge of LangChain basics.
* **Hugging Face**: A platform and community for artificial intelligence, offering some LLMs for local download and use.
* **LLM**: A command-line tool that enables you to download and use open-source LLMs locally, with plugins for various models, including GPT4All and Meta's Llama.
* **Ollama**: A simple, point-and-click installation process for running Llama models on your desktop, with a user-friendly interface for chatting with your own documents.
* **h2oGPT**: A desktop application that allows you to chat with your own documents using natural language and get a generative AI response, with a basic version available for download.
* **PrivateGPT**: A tool that enables you to query your own documents using natural language and get a generative AI response, with a simplified version available for non-experts.
* **Jan**: An open-source project that offers a simple interface for chatting with local models, with the ability to upload files and chat with documents (although with some limitations).
* **Opera**: A convenient, but potentially less private, way to chat with local models using the developer version of Opera, with some limitations.
* **Chat with RTX**: A simple interface for answering questions about a directory of documents using Llama 2 LLM, with some limitations and requirements (e.g., Nvidia GeForce RTX 30 Series or higher GPU).
* **llamafile**: A tool that allows developers to turn critical portions of large language models into executable files, with a simple setup process, but some limitations (e.g., currently not ideal for Windows).
* **LocalGPT**: A spinoff of PrivateGPT with more model options and detailed instructions, but with a warning that running on a CPU alone will be slow.
* **LM Studio**: A desktop app with a clean interface for running chats, but requires knowledge of model selection and has some limitations (e.g., no built-in option for running LLM over your own data).
* **LangChain**: A framework for creating end-to-end generative AI applications, requiring knowledge of LangChain basics.
* **Hugging Face**: A platform and community for artificial intelligence, offering some LLMs for local download and use.
The "LLM" toolkit provides a command-line utility and Python library for interacting with large language models. It enables users to run prompts from the terminal, store responses in SQLite databases, generate embeddings, and more. This comprehensive guide includes topics such as setup, usage, OpenAI models, other models, embeddings, plugins, model aliases, Python API, prompt templates, logging, related tools, CLI reference, contributing, and changelog.
* **New Feature:** `openai-to-sqlite` tool now allows enriching data in a SQLite database using OpenAI's GPT3.5 model.
* **Sentiment Analysis Example:**
+ Update a `sentiment` column in a `messages` table using `chatgpt()` function.
* **Sentiment Analysis Example:**
+ Update a `sentiment` column in a `messages` table using `chatgpt()` function.
The author has also automated their weeknotes by using an Observable notebook, which generates the "releases this week" and "TILs this week" sections.
The notebook fetches TILs from the author's Datasette, grabs releases from GitHub, and assembles a markdown string for the new post.
* `llm` CLI tool for running prompts against large language models
* Automation of weeknotes using an Observable notebook
* Notebook generates "releases this week" and "TILs this week" sections
* Tool stores prompts and responses in a SQLite database
The notebook fetches TILs from the author's Datasette, grabs releases from GitHub, and assembles a markdown string for the new post.
* `llm` CLI tool for running prompts against large language models
* Automation of weeknotes using an Observable notebook
* Notebook generates "releases this week" and "TILs this week" sections
* Tool stores prompts and responses in a SQLite database
