Updated diagram to read fastAPI for server

README.md

@@ -17,7 +17,7 @@ For more information on the recipes concept, please see see [here](https://towar
 
 Data recipes have two types: (i) Exact memories, eg '*What is the population of Mali?*' which can be served directly to the user when they ask this question; (ii) Generic skills which can be run when requested for a scenario not in memory, eg a skill for 'What is the population of country X?' which can be called when the user asks something like '*What is the population of Nigeria?*'. In both cases the match to the user's intent is made using semantic search with LLM-reranking.
 
-Given the rapidly changing landscape of LLMs, we have tried as much as possible to implement data recipes in such a way that it can be integrated with various semantic architectures and frameworks. By implementing recipes using a recipes server (powered by [Robocorps actions server](https://github.com/robocorp/robocorp#readme)), it can be called from [Open AI assistant](https://platform.openai.com/docs/assistants/overview) actions and [Copilot Studio](https://www.microsoft.com/en-us/microsoft-copilot/microsoft-copilot-studio) as well from any custom code. Also included in this repo is an example of using recipes via OpenAI format plugins, as supported by frameworks such as [semantic kernel](https://learn.microsoft.com/en-us/semantic-kernel/overview/?tabs=Csharp). 
+Given the rapidly changing landscape of LLMs, we have tried as much as possible to implement data recipes in such a way that it can be integrated with various semantic architectures and frameworks. By implementing recipes using a recipes server (powered by FastAPI), it can be called from [Open AI assistant](https://platform.openai.com/docs/assistants/overview) actions and [Copilot Studio](https://www.microsoft.com/en-us/microsoft-copilot/microsoft-copilot-studio) as well from any custom code. Also included in this repo is an example of using recipes via OpenAI format plugins, as supported by frameworks such as [semantic kernel](https://learn.microsoft.com/en-us/semantic-kernel/overview/?tabs=Csharp). 
 
 Data recipes supports datasources accessed via API, but in some cases it is preferable to ingest data in order to leverage LLM SQL capabilities. We include an initial set of data sources specific to humanitarian response in the ingestion module, which can be extended to include additional sources as required.