Merge branch 'main' & updates to chatbots

Author: neagualexa

.github/workflows/docs.yml

@@ -64,7 +64,7 @@ jobs:
         id: build-docs
         if: github.event_name != 'push' || github.ref_name != github.event.repository.default_branch
         env:
-          API_KEY: ${{ secrets.API_KEY }}
+          API_KEY: ${{ secrets.API_KEY_2 }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: poetry run mkdocs build
 
@@ -79,6 +79,7 @@ jobs:
       - name: Deploy docs
         if: github.event_name == 'push' && github.ref_name == github.event.repository.default_branch
         env:
-          API_KEY: ${{ secrets.API_KEY }}
+          API_KEY: ${{ secrets.API_KEY_2 }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          ENABLE_EVALDOCS: true
         run: poetry run mkdocs gh-deploy --force

docs/.DS_Store

@@ -16,7 +16,7 @@ The Chatbots have at their basis a [Large Language Model (LLM)](https://en.wikip
 
 Currently the students have access to the following AI Chatbots. Many others are in development.
 
-1. Informational Chatbot
+#### 1. Informational Chatbot
 
 This chatbot aims to complete all the relevant tasks the student requests based on the current Question they are working on. The Chatbot is aware of the Question details, answer, worked solution and guidance from the lecturer.
 
@@ -29,6 +29,32 @@ Helping approach: encourages self-discovery of the answer, but will reveal the s
 </code>
 </pre>
 
+#### 2. Concise Chatbot
+
+This chatbot aims to concisely respond to all relevant tasks the student requests based on the current Question they are working on. The Chatbot is aware of the Question details, answer, worked solution and guidance from the lecturer.
+
+Some technical details:
+<pre style="white-space: pre-wrap;">
+<code>LLM model: Gemini-2.0-flash (Google)
+response time (on average): 10 seconds
+
+Helping approach: provides short, direct answers without extra detail
+</code>
+</pre>
+
+#### 3. Reflective Chatbot
+
+This chatbot aims to respond to all relevant tasks the student requests by emphasising self-reflection through asking the student follow-up questions. The Chatbot is aware of the Question details, answer, worked solution and guidance from the lecturer.
+
+Some technical details:
+<pre style="white-space: pre-wrap;">
+<code>LLM model: gpt-4o-mini (OpenAI)
+response time (on average): 10 seconds
+
+Helping approach: always responds with a follow-up question
+</code>
+</pre>
+
 ## AI Chatbot Development
 
 Are you interested in developing your own chatbot? Then please check out the [Quickstart guide](quickstart.md) to develop and deploy your own AI chat agent for Lambda Feedback.

docs/advanced/chatbot_agents/info.md docs/advanced/chat_functions/info.mddocs/advanced/chatbot_agents/info.md renamed to docs/advanced/chat_functions/info.md

@@ -2,4 +2,4 @@
 
 Documentation for each of the functions registered to the LambdaFeedback platform are pulled in this section automatically. This is done using a custom MkDocs plugin [EvalDocsLoader](https://github.com/lambda-feedback/EvalDocsLoader).
 
-If you can't see any documentation files under this section, please contact an admin.
+If you can't see any documentation files as subsections here, please contact an admin.

docs/advanced/chatbot_agents/local.md docs/advanced/chat_functions/local.mddocs/advanced/chatbot_agents/local.md renamed to docs/advanced/chat_functions/local.md

@@ -1,29 +1,28 @@
 # Advanced users
 
-Advanced users can develop their own evaluation functions.
 
-## Evaluation functions
+## Microservices
 
-Evaluation functions are responsible for taking in a user's response, comparing it with a correct answer, and providing feedback to the frontend application. Living as containserized Lambda functions on the cloud, they are infinitely customisable and language-agnostic. Content authors should be able to create their own at will. However, we are aware that in a lot of cases, this grading logic will be similar, which is why a few functions have already been created.
+The fundamental idea of Lambda Feedback is that it calls external microservices to provide interaction with users. There are two types of microservice: 
 
-[Evaluation functions - Quickstart Guide](evaluation_functions/quickstart.md){ .md-button .md-button--primary }
+Evaluate a student response and provide feedback: 
+[Evaluation functions - Quickstart Guide](evaluation_functions/quickstart.md){ .md-button .md-button--primary style="width: 400px;"}
 
-## Response areas
+Dialogic conversations with students:<br>
+[Chat functions - Quickstart guide ](chatbot_agents/quickstart.md){ .md-button .md-button--primary style="width: 400px;"}
 
-Response areas are components in the frontend where student users can enter a response. The response is sent to the evaluation function, which returns feedback to the response area. In the alpha version response areas are built into the software (rather than being modular) so are not straightforward to redevelop. This website catalogues the basic behaviour of response areas, to inform developers of evaluation functions.
+All microservices are called over http. There is complete freedom in their implementation. Lambda Feedback also provides families of deployed microservices, using open source code available in our public GitHub repositories.
 
-[Response areas - overview](response_areas/overview.md){ .md-button .md-button--primary}
+This section of documentation is to help developers of microservices. The documentation is written assuming you have basic developer skills.
 
-## AI Chatbot Agents
+In addition to microservices, this 'Advanced' section caters to administrators of Lambda Feedback tenants; and to developers of interactive response areas, that can be published within our web-stack via discussion with the developers. 
 
-Chatbot agents are AI Assistants that students can chat with to ask for help or further explanations regarding the Question that they are working on. Each Agent has its own personality and approach to assisting the students.
+## Response areas
 
-[Chatbot Agents - Quickstart guide](chatbot_agents/quickstart.md){ .md-button .md-button--primary}
+Response areas are components in the frontend where student users can enter a response. The response is sent to the evaluation function, which returns feedback to the response area. In the alpha version response areas are built into the software (rather than being modular) so are not straightforward to redevelop. This website catalogues the basic behaviour of response areas, to inform developers of evaluation functions.
 
-## System Architecture
+[Response areas - overview](response_areas/overview.md){ .md-button .md-button--primary style="width: 400px;"}
 
-- Technologies
-- Deployment pipelines
-- Hierarchy
+## Administrators
 
-## Future Features
+Content to be added.