Download the PHP package llm-speak/core without Composer
On this page you can find all versions of the php package llm-speak/core. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Download llm-speak/core
More information about llm-speak/core
Files in llm-speak/core
Package core
Short Description Universal LLM interface for Laravel applications.
License MIT
FAQ
Example:
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Informations about the package core
LLM Speak
A Laravel package to interact with LLMs using Eloquent-like syntax.
Installation
1) Install via Composer
2) Publish configuration (optional)
3) Install Drivers
Drivers include:
- OpenAI Compatible — Embeddings, Inferencing, Chat Completions
- Ollama — Embeddings, Inferencing, Chat Completions
- LMStudio — Embeddings, Inferencing, Chat Completions
- MistralAI — Embeddings, Inferencing, Chat Completions
- Gemini — Embeddings, Inferencing, Chat Completions
- xAI — Tokenization, Chat Completions
- OpenRouter — Inferencing, Chat Completions
- Anthropic — Chat Completions
- OpenAI Responses — Chat Completions
- HuggingFace — Chat Completions
Usage
Create a Neural Model
- Create a Neural Model that extends the type of interaction you want (e.g., Tokenization, Embeddings, Inference, Completions).
- Available Neural Models:
TokenizationModel,EmbeddingsModel,InferenceModel,CompletionsModel. - When creating the model, the default provider and model are read from the model's config.
- You can override by setting the model's
$connectionand$model_idproperties.
Chat Completions
Configure your provider in config/chat-completions.php:
Use the Completions model to have a model reply to your input.
Instance usage
Fluent usage
Manual builder usage
Advanced usage
These additional parameters can be set on the Completions model like so.
NOTE: Not all providers support all these parameters.
OneShot Inferencing
Configure your provider in config/inferencing.php:
Use the Inference model to have a model response to your input.
Instance usage
Fluent usage
Manual builder usage
Advanced usage
These additional parameters can be set on the Embeddings model like so.
NOTE: Not all providers support all these parameters.
Vector Embeddings
Configure your provider in config/vector-embeddings.php:
Use the Embeddings model to convert text to vectors.
Instance usage
Fluent usage
Manual builder usage
Advanced usage
These additional parameters can be set on the Embeddings model like so.
NOTE: Not all providers support all these parameters.
Tokenization
Configure your provider in config/text-tokenization.php:
Use the Tokenization model to convert text to tokens.
Instance usage
Fluent usage
Manual builder usage
All versions of core with dependencies
ext-json Version *
spatie/laravel-data Version ^4.11
lorisleiva/laravel-actions Version ^2.6
projectsaturnstudios/quickuuid Version ^0.2.0
projectsaturnstudios/laravel-design-patterns Version ^0.1.0