Renamed EDI to ERI

Author: SommerEngineering

README.md

@@ -3,7 +3,7 @@ permalink: /
 ---
 # MindWork AI
 
-MindWork AI is the GitHub organization behind [AI Studio](https://github.com/MindWorkAI/AI-Studio). In addition to AI Studio, we offer other repositories, such as [EDI](https://github.com/MindWorkAI/EDI), the "(E)xternal (D)ata AP(I)" for AI Studio.
+MindWork AI is the GitHub organization behind [AI Studio](https://github.com/MindWorkAI/AI-Studio). In addition to AI Studio, we offer other repositories, such as [ERI](https://github.com/MindWorkAI/ERI), the "(E)xternal (R)etrieval (I)nterface" for AI Studio and other LLM tools.
 
 
 ## AI Studio
@@ -14,13 +14,13 @@ MindWork AI is the GitHub organization behind [AI Studio](https://github.com/Min
 ![MindWork AI Studio - Assistants](media/AI%20Studio%20Assistants.png)
 
 
-## EDI - (E)xternal (D)ata AP(I)
+## ERI - (E)xternal (R)etrieval (I)nterface
 
-The [EDI](https://github.com/MindWorkAI/EDI) is the External Data API for [AI Studio](https://github.com/MindWorkAI/AI-Studio). The EDI acts as a contract between decentralized data sources and AI Studio. The EDI is implemented by the data sources, allowing them to be integrated into AI Studio later. This means that the data sources assume the server role and AI Studio assumes the client role of the API. This approach serves to realize a [Retrieval-Augmented Generation](https://en.wikipedia.org/wiki/Retrieval-augmented_generation) (RAG) process with external data. You can imagine it like this: Hypothetically, when Wikipedia implemented the EDI, it would vectorize all pages using an [embedding method](https://en.wikipedia.org/wiki/Word_embedding). All of Wikipedia's data would remain with Wikipedia, including the [vector database](https://en.wikipedia.org/wiki/Vector_database) (decentralized approach). Then, any AI Studio user could add Wikipedia as a data source to significantly reduce the hallucination of the LLM in knowledge questions.
+The [ERI](https://github.com/MindWorkAI/ERI) is the External Retrieval Interface for [AI Studio](https://github.com/MindWorkAI/AI-Studio) and other tools. The ERI acts as a contract between decentralized data sources and, e.g., AI Studio. The ERI is implemented by the data sources, allowing them to be integrated into AI Studio later. This means that the data sources assume the server role and AI Studio (or any other LLM tool) assumes the client role of the API. This approach serves to realize a [Retrieval-Augmented Generation](https://en.wikipedia.org/wiki/Retrieval-augmented_generation) (RAG) process with external data. You can imagine it like this: Hypothetically, when Wikipedia implemented the ERI, it would vectorize all pages using an [embedding method](https://en.wikipedia.org/wiki/Word_embedding). All of Wikipedia's data would remain with Wikipedia, including the [vector database](https://en.wikipedia.org/wiki/Vector_database) (decentralized approach). Then, any AI Studio user could add Wikipedia as a data source to significantly reduce the hallucination of the LLM in knowledge questions.
 
-When you want to integrate your own local data into AI Studio, you don't need an EDI. Instead, AI Studio will offer an RAG process for this in the future. Is your organization interested in integrating internal company data into AI Studio? [Here](swagger-ui.html) you will find the [interactive documentation](swagger-ui.html) of the related OpenAPI interface.
+When you want to integrate your own local data into AI Studio, you don't need an ERI. Instead, AI Studio will offer an RAG process for this in the future. Is your organization interested in integrating internal company data into AI Studio? [Here](swagger-ui.html) you will find the [interactive documentation](swagger-ui.html) of the related OpenAPI interface.
 
 Links:
-- [EDI repository with example implementation in .NET / C#](https://github.com/MindWorkAI/EDI)
+- [ERI repository with example implementation in .NET / C#](https://github.com/MindWorkAI/ERI)
 - [Interactive documentation aka Swagger UI](swagger-ui.html)
-- [EDI specification](edi-specification.json), which you could use with tools like [OpenAPI Generator](https://github.com/OpenAPITools/openapi-generator).
+- [ERI specification](eri-specification.json), which you could use with tools like [OpenAPI Generator](https://github.com/OpenAPITools/openapi-generator).

edi-specification.json eri-specification.json

@@ -1,8 +1,8 @@
 {
   "openapi": "3.0.1",
   "info": {
-    "title": "EDI - (E)xternal (D)ata AP(I) for AI Studio",
-    "description": "This API serves as a contract between AI Studio and any external data sources for RAG\n(retrieval-augmented generation). AI Studio acts as the client (the augmentation and\ngeneration parts) and the data sources act as the server (the retrieval part). The data\nsources implement some form of data retrieval and return a suitable context to AI Studio.\nAI Studio, in turn, handles the integration of appropriate LLMs (augmentation & generation).\nData sources can be document or graph databases, or even a file system, for example. They\nwill likely implement an appropriate retrieval process by using some kind of embedding.\nHowever, this API does not inherently require any embedding, as data processing is\nimplemented decentralized by the data sources.",
+    "title": "ERI - (E)xternal (R)etrieval (I)nterface",
+    "description": "This API serves as a contract between LLM tools like AI Studio and any external data sources for RAG\n(retrieval-augmented generation). The tool, e.g., AI Studio acts as the client (the augmentation and\ngeneration parts) and the data sources act as the server (the retrieval part). The data\nsources implement some form of data retrieval and return a suitable context to the LLM tool.\nThe LLM tool, in turn, handles the integration of appropriate LLMs (augmentation & generation).\nData sources can be document or graph databases, or even a file system, for example. They\nwill likely implement an appropriate retrieval process by using some kind of embedding.\nHowever, this API does not inherently require any embedding, as data processing is\nimplemented decentralized by the data sources.",
     "version": "v1"
   },
   "paths": {
@@ -515,17 +515,17 @@
       }
     },
     "securitySchemes": {
-      "EDI_Token": {
+      "ERI_Token": {
         "type": "apiKey",
-        "description": "Enter the EDI token yielded by the authentication process at /auth.",
+        "description": "Enter the ERI token yielded by the authentication process at /auth.",
         "name": "token",
         "in": "header"
       }
     }
   },
   "security": [
     {
-      "EDI_Token": [ ]
+      "ERI_Token": [ ]
     }
   ]
 }