Search

More Filters

Show More
Add Listing
Go Back

LLPhant

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

LLPhant is a PHP framework designed to let developers build generative AI applications and retrieval-augmented systems using multiple LLM providers. It provides a higher-level, opinionated API on top of model clients to simplify common tasks such as chat generation, image generation, vision input, speech transcription and translation, embeddings creation, vector storage and semantic search. The project targets PHP 8.1+ and integrates with popular web frameworks like Symfony and Laravel. It supports multiple model backends including OpenAI-compatible endpoints, Anthropic, Mistral, Ollama and LocalAI, and includes adapters for many vector stores. The repo bundles tooling for creating document pipelines, question-answering flows, tool/function invocation, chat sessions (memory), guardrails and evaluation strategies. Installation is via Composer so it can be included in PHP projects to accelerate building chatbots, RAG systems, agent-like automations and other generative AI features.

Links

Stars
1314
App URL
https://github.com/LLPhant/LLPhant
Github Repository
https://github.com/LLPhant/LLPhant/blob/main/README.md

Categorization

App Details

Features
Provides modular components for generative AI workflows including chat clients with streaming and system messages, vision-enabled chat that accepts image inputs, image generation, and audio transcription and translation. Offers an embeddings pipeline with data readers, document splitting, formatting and multiple embedding generator implementations. Includes many VectorStore adapters such as in-memory, filesystem, Doctrine (pgvector/MariaDB), Qdrant, Redis, Elasticsearch/OpenSearch, Milvus, ChromaDB, AstraDB and Typesense. Implements QuestionAnswering with retrieval transformers, multi-query reformulation, siblings expansion and reranking. Supports tools/functions integration so LLMs can call local PHP methods. Adds guardrails for output validation and retry/block strategies. Ships an evaluation suite with criteria, embedding-distance, string-comparison and trajectory evaluators plus JSON/XML/regex/token/word validators and A/B pairwise comparison utilities.
Use Cases
LLPhant lowers the barrier to add production-ready generative AI features to PHP applications by abstracting model differences and integrating retrieval, storage and evaluation components. Developers can implement semantic search, RAG-based chatbots, summarizers, personalized content workflows and autonomous agent prototypes using provided building blocks. The framework centralizes embedding creation, vector storage adapters and retrieval strategies so projects can switch engines or stores with minimal code changes. Tool invocation and guardrails enable safer, action-oriented assistants that can call local services while validators and evaluators support automated testing and quality monitoring. Composer installation and compatibility with Symfony and Laravel make it straightforward to include LLPhant in existing stacks and to iterate from prototypes to deployments while leveraging multiple LLM backends and vector databases.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*