Agentic Applications with Symfony

A chat interface is by far not all what you could build with Symfony and Large Language Models. And agentic applications are the next level of integrating AI - not only in your code, but also in your business.
Let's have a look together on some basic concepts and hands-on examples of letting AI take over more responsibilities in a well-defined and automated manner.

Talk was given on April 3rd at SymfonyLive Berlin.

Transcript

1. Agentic Applications with Symfony Christopher Hertel ‐ SymfonyLive Berlin 2025 1
2. Agenda Theory & Terminology Models, Context, RAG, and more Evolution from LLM to Agentic Code Examples with Symfony Model Context Protocol Distributed Agentic Applications 2
3. Christopher Hertel Software Engineer Focus on PHP, Symfony and GenAI Working on Tech Program of 3
4. Slides Scan and follow the slides online 4
5. Theory & Terminology Models, Context, RAG, and more 5
6. Models Language Model Trained to generate text based on text input Strong Competition & Fast Innovation OpenAI, Google, Meta, Anthropic, Mistral, and more Various Capabilities Streaming, structured output, multi-modal, real-time, tool calling Reasoning Model Decision making, less prompt engineering & more autonomous 6
7. Platforms Model Vendor OpenAI, Anthropic, Mistral, Google, ... General Cloud Provider Azure (GitHub), Google, AWS, ... Specialized Cloud Provider HuggingFace, Replicate, OpenRouter, ... Local Runtimes GPT4All, Ollama, ONNX Runtime, ... 7
8. Chain Chain of Calls Designed for multi-step interaction with models Combination of Things Platform, Models, System Prompts, Capabilities, etc. LangChain Most Famous LLM framework (Pyhton & TypeScript) 8
9. Plain Model Chain9
10. Context Stateless API Pre-trained, fine-tuned, but API "forgets" Limitation Size of context varies per model, but limited Powerful Control Mechanism Efficient to steer and evaluate the models generation 10
11. Context Example 11
12. RAG Architecture Retrieval Augmented Generation Dynamically inject information into context Improves Accuracy and Relevance More context for the model to work with, based on input Vector Stores Classic RAG combines embedding vectors and similarity search Improvement Techniques Pre-processing, Multi-Query, Reranking, and more 12
13. Simple RAG13
14. Tool Calling App Provides Tools Exposed to tool via JSON Schema definition as part of API call Model Invokes Tool As a intermediate response the model invokes a tool (or multiple) Tool Result Result of tool call provided as next call to model Instrumentation Log and analyze tool calls, model invocations, and results 14
15. Tool Calling15
16. Agent vs. Agentic 16
17. PHP Libraries Listicle on GitHub LLPhant theodo-group/llphant Prism prism-php/prism LLM Chain php-llm/llm-chain Today 17
18. Evolution from LLM to Agent Code Examples with PHP & Symfony 18
19. Install LLM Chain composer require php-llm/llm-chain 19
20. Plain Model Chain20
21. Plain Model Chain use PhpLlm\LlmChain\Bridge\OpenAI\{GPT, PlatformFactory}; use PhpLlm\LlmChain\Chain; use PhpLlm\LlmChain\Model\Message\{Message, MessageBag}; $platform = PlatformFactory::create($apiKey); $chain = new Chain($platform, new GPT()); $messages = new MessageBag( Message::forSystem('You are a pirate and you write funny.'), Message::ofUser('What is the Symfony framework?'), ); $response = $chain->call($messages); echo $response->getContent(); 21
22. Symfony Integration composer require php-llm/llm-chain-bundle 22
23. Bundle Configuration # config/packages/llm_chain.yaml llm_chain: platform: openai: # or anthropic, azure, google, more to come ... api_key: '%env(OPENAI_API_KEY)%' chain: default: model: name: 'GPT' version: 'gpt-4o-mini' system_prompt: 'You are a pirate and you write funny.' 23
24. Usage in Symfony final readonly class SomeService { public function __construct(private ChainInterface $chain) { } public function someMethod(string $message): string { $messages = new MessageBag(Message::ofUser($message)); $response = $this->chain->call($messages); return $response->getContent(); } } 24
25. Simple RAG25
26. Tool Calling26
27. Tool Calling use PhpLlm\LlmChain\Chain\Toolbox\Attribute\AsTool; use Symfony\Component\Clock\ClockInterface; #[AsTool('clock', description: 'Returns the current date and time.')] final readonly class Clock { public function __construct(private ClockInterface $clock) { } public function __invoke(): string { return $this->clock->now()->format('Y-m-d H:i:s'); } } That's it already! 27
28. Agentic RAG28
29. Bundle Configuration # config/packages/llm_chain.yaml llm_chain: # Platform & Chain Configuration ... store: chroma_db: # or Azure Search, MongoDB, Pinecone, more to come ... symfonyblog: { collection: 'symfony_blog' } embedder: default: model: { name: 'Embeddings', version: 'text-embedding-ada-002' } services: _defaults: { autowire: true, autoconfigure: true } PhpLlm\LlmChain\Chain\Toolbox\Tool\SimilaritySearch: ~ 29
30. Agentic Application30
31. Bundle Configuration # config/packages/llm_chain.yaml llm_chain: # Platform Configuration ... chain: wikipedia: model: name: 'GPT' version: 'gpt-4o-mini' system_prompt: | Please answer the users question based on information of Wikipedia and provide a link to the article. tools: - 'PhpLlm\LlmChain\Chain\Toolbox\Tool\Wikipedia' 31
32. AI Tools32
33. Bundle Configuration Stack and isolate chains to build a more complex chain. # config/packages/llm_chain.yaml llm_chain: # Platform Configuration ... chain: complex_chain: # Model Configuration ... tools: # Chain in chain 🤯 - service: 'llm_chain.chain.blog' name: 'symfony_blog' description: 'Can answer questions based on the Symfony blog.' is_chain: true 33
34. Model Context Protocol Distributed Agentic Applications 34
35. Model Context Protocol (MCP) Open Sourced Protocol by Anthropic Only release late 2024, already exploded to everywhere Standardizes Five Aspects Resources, Prompts, Tools, Sampling, Roots Two Main Components Defines MCP Server and MCP Client JSON-RPC with Two Transports STDIO and Server-Sent-Events 35
36. General Architecture36
37. Agentic Application37
38. Model Context Protocol38
39. PHP MCP SDK No official SDK for PHP 39
40. But ... composer require php-llm/mcp-bundle 40
41. Bundle Configuration # config/packages/mcp.yaml mcp: app: 'app' # Application name to be exposed to clients version: '1.0.0' # Application version to be exposed to clients # Configure this application to act as a MCP server # For now ONLY TOOLS client_transports: stdio: true # Enable STDIO via command sse: true # Enable Server-Sent Event via controller # Configure MCP servers to be used by this application # NOT IMPLEMENTED YET servers: name: transport: 'stdio' # Transport method to use, either 'stdio' or 'sse' stdio: command: 'php /path/bin/console mcp' # Command to execute to start arguments: [] # Arguments to pass to the command sse: url: 'http://localhost:8000/sse' # URL to SSE endpoint of MCP serv 41
42. Work In Progress But let's have a look ... 42
43. Thank You! Any Questions? 43
44. Useful Links LLM Chain: github.com/php-llm/llm-chain Bundle: github.com/php-llm/llm-chain-bundle MCP SDK (WIP): github.com/php-llm/mcp-sdk Bundle (WIP): github.com/php-llm/mcp-bundle Other Libs: github.com/php-llm/ecosystem Model Context Protocol: modelcontextprotocol.io 44