Add allow-llm-calls attribute, add instructions to use GA keys

Author: adam-cowley

asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/1-getting-started/lesson.adoc

@@ -5,7 +5,7 @@
 :disable-cache: true
 
 We have created a link:https://github.com/neo4j-graphacademy/genai-workshop[repository^] for this workshop.
-It contains the starter code and resources you need. 
+It contains the starter code and resources you need.
 
 A blank Neo4j Sandbox instance has also been created for you to use during this course.
 
@@ -48,7 +48,7 @@ pip install -r requirements.txt
 
 == Setup the environment
 
-Create a copy of the `.env.example` file and name it `.env`. 
+Create a copy of the `.env.example` file and name it `.env`.
 Fill in the required values.
 
 [source]
@@ -57,7 +57,7 @@ Fill in the required values.
 include::{repository-raw}/main/.env.example[]
 ----
 
-Add your Open AI API key (`OPENAI_API_KEY`), which you can get from link:https://platform.openai.com[platformn.openai.com].
+Add your Open AI API key (`OPENAI_API_KEY`), which you can get from link:https://platform.openai.com[platform.openai.com].
 
 Update the Neo4j sandbox connection details:
 

asciidoc/courses/llm-chatbot-python/course.adoc

@@ -7,10 +7,11 @@
 // :video: https://www.youtube.com/embed/vVCHJFa01gA
 :key-points: Building a Neo4j-backed Chatbot, Neo4j & Langchain, Neo4j & Streamlit
 :repository: neo4j-graphacademy/llm-chatbot-python
+:allow-llm-calls: true
 
 == Course Description
 
-In this hands-on course, you will use the knowledge obtained from the link:/courses/llm-fundamentals[Neo4j & LLM Fundamentals course^] to create a Movie Recommendation Chatbot backed by a Neo4j database.
+In this hands-on course, you will use the knowledge from the link:/courses/llm-fundamentals[Neo4j & LLM Fundamentals course^] to create a Movie Recommendation Chatbot backed by a Neo4j database.
 
 You will take a simple chat interface that repeats the user's input and modify it to answer questions about movies via the Neo4j Recommendations Dataset using _GPT 3.5 Turbo_, complete with conversational history.
 

asciidoc/courses/llm-chatbot-typescript/course.adoc

@@ -12,6 +12,7 @@
 :reward-form: https://graphacademy.neo4j.com/account/rewards/llm-chatbot-typescript/
 :reward-provider: printful
 :reward-product-id: @65f874e831d488,@65f875094279d1
+:allow-llm-calls: true
 
 == Course Description
 at

asciidoc/courses/llm-fundamentals/course.adoc

@@ -7,6 +7,7 @@
 :usecase: recommendations
 // :video: https://www.youtube.com/embed/vVCHJFa01gA
 :key-points: Neo4j and Generative AI, Grounding LLMs with Neo4j, Using Neo4j with Langchain
+:allow-llm-calls: true
 
 == Course Description
 
@@ -38,7 +39,7 @@ To complete the practical tasks within this course, you will need an link:https:
 === What you will learn
 
 * Retrieval Augmented Generation (RAG) and its role in grounding LLM generated content
-* Using Vector and full text indexes in Neo4j to perform similarity and keyword search
+* Using Vector and full-text indexes in Neo4j to perform similarity and keyword search
 * Coordinating your LLM interactions with Langchain chains, agents and tools
 
 [.includes]

asciidoc/courses/llm-fundamentals/modules/3-intro-to-langchain/lessons/2-initialising-the-llm/lesson.adoc

@@ -20,7 +20,37 @@ This course includes instructions for using link:https://openai.com/[OpenAI^], b
 
 [NOTE]
 .Using OpenAI
-If you wish to use OpenAI and follow this course's practical activities, you must create an account and set up billing.
+====
+We have generated an OpenAI API key for you to use through our OpenAI Proxy for the duration of this course using a proxy.
+The API key will be limited to 5 requests every two minutes.
+
+
+.Environment Variable
+[source,env,subs="attributes+"]
+----
+OPENAI_API_KEY={llm-api-key}
+----
+
+You must also set the `base_url` parameter to use our proxy server.
+
+.Setting the Proxy
+[source,python,subs="attributes+"]
+----
+from openai import OpenAI
+
+model = OpenAI(
+  api_key="{llm-api-key}",
+  base_url="https://graphacademy.neo4j.com/api/llm/v1/"
+)
+----
+
+You can always use an existing OpenAI API key and omit the `base_url` argument.
+
+
+====
+
+
+
 
 == Setup
 

src/constants.ts

@@ -64,3 +64,4 @@ export const ATTRIBUTE_DESCRIPTION = 'description'
 export const ATTRIBUTE_QUESTIONS = 'questions'
 export const ATTRIBUTE_PASS_PERCENTAGE = 'pass-percentage'
 export const ATTRIBUTE_KEY_POINTS = 'key-points'
+export const ATTRIBUTE_ALLOW_LLM_CALLS = 'allow-llm-calls'

src/services/merge-courses.ts

@@ -5,7 +5,7 @@ import { Session, ManagedTransaction } from 'neo4j-driver';
 import { loadFile } from '../modules/asciidoc'
 import { getDriver } from '../modules/neo4j';
 import { CourseToImport, LessonToImport, ModuleToImport, QuestionToImport } from '../types';
-import { ASCIIDOC_DIRECTORY, ATTRIBUTE_CAPTION, ATTRIBUTE_CATEGORIES, ATTRIBUTE_CERTIFICATION, ATTRIBUTE_CLASSMARKER_ID, ATTRIBUTE_CLASSMARKER_REFERENCE, ATTRIBUTE_DISABLE_CACHE, ATTRIBUTE_DURATION, ATTRIBUTE_LAB, ATTRIBUTE_LANGUAGE, ATTRIBUTE_NEXT, ATTRIBUTE_OPTIONAL, ATTRIBUTE_REDIRECT, ATTRIBUTE_REPOSITORY, ATTRIBUTE_SANDBOX, ATTRIBUTE_STATUS, ATTRIBUTE_THUMBNAIL, ATTRIBUTE_TRANSLATIONS, ATTRIBUTE_REWARD_FORM, ATTRIBUTE_REWARD_IMAGE, ATTRIBUTE_REWARD_PRODUCT_ID, ATTRIBUTE_REWARD_PROVIDER, ATTRIBUTE_TYPE, ATTRIBUTE_UPDATED_AT, ATTRIBUTE_USECASE, ATTRIBUTE_VIDEO, COURSE_DIRECTORY, DEFAULT_COURSE_STATUS, DEFAULT_COURSE_THUMBNAIL, DEFAULT_LANGUAGE, DEFAULT_LESSON_TYPE, STATUS_DISABLED, ATTRIBUTE_REWARD_TYPE, ATTRIBUTE_DESCRIPTION, ATTRIBUTE_QUESTIONS, ATTRIBUTE_PASS_PERCENTAGE, ATTRIBUTE_KEY_POINTS, ATTRIBUTE_BRANCH } from '../constants';
+import { ASCIIDOC_DIRECTORY, ATTRIBUTE_CAPTION, ATTRIBUTE_CATEGORIES, ATTRIBUTE_CERTIFICATION, ATTRIBUTE_CLASSMARKER_ID, ATTRIBUTE_CLASSMARKER_REFERENCE, ATTRIBUTE_DISABLE_CACHE, ATTRIBUTE_DURATION, ATTRIBUTE_LAB, ATTRIBUTE_LANGUAGE, ATTRIBUTE_NEXT, ATTRIBUTE_OPTIONAL, ATTRIBUTE_REDIRECT, ATTRIBUTE_REPOSITORY, ATTRIBUTE_SANDBOX, ATTRIBUTE_STATUS, ATTRIBUTE_THUMBNAIL, ATTRIBUTE_TRANSLATIONS, ATTRIBUTE_REWARD_FORM, ATTRIBUTE_REWARD_IMAGE, ATTRIBUTE_REWARD_PRODUCT_ID, ATTRIBUTE_REWARD_PROVIDER, ATTRIBUTE_TYPE, ATTRIBUTE_UPDATED_AT, ATTRIBUTE_USECASE, ATTRIBUTE_VIDEO, COURSE_DIRECTORY, DEFAULT_COURSE_STATUS, DEFAULT_COURSE_THUMBNAIL, DEFAULT_LANGUAGE, DEFAULT_LESSON_TYPE, STATUS_DISABLED, ATTRIBUTE_REWARD_TYPE, ATTRIBUTE_DESCRIPTION, ATTRIBUTE_QUESTIONS, ATTRIBUTE_PASS_PERCENTAGE, ATTRIBUTE_KEY_POINTS, ATTRIBUTE_BRANCH, ATTRIBUTE_ALLOW_LLM_CALLS } from '../constants';
 import { courseOverviewPath, getDateAttribute, getOrderAttribute } from '../utils';
 
 const loadCourses = (): CourseToImport[] => {
@@ -87,6 +87,7 @@ const loadCourse = (courseFolder: string): CourseToImport => {
         classmarkerReference: file.getAttribute(ATTRIBUTE_CLASSMARKER_REFERENCE, null),
         questions: file.getAttribute(ATTRIBUTE_QUESTIONS, null),
         passPercentage: file.getAttribute(ATTRIBUTE_PASS_PERCENTAGE, null),
+        allowsLLMCalls: file.getAttribute(ATTRIBUTE_ALLOW_LLM_CALLS, 'false') === 'true',
         attributes: {
             rewardType: file.getAttribute(ATTRIBUTE_REWARD_TYPE, null),
             rewardForm: file.getAttribute(ATTRIBUTE_REWARD_FORM, null),
@@ -216,6 +217,7 @@ const mergeCourseDetails = (tx: ManagedTransaction, courses: CourseToImport[]) =
             c.classmarkerReference = course.classmarkerReference,
             c.questions = toInteger(course.questions),
             c.passPercentage = toInteger(course.passPercentage),
+            c.allowsLLMCalls = course.allowsLLMCalls,
             c += course.attributes
 
         FOREACH (_ IN CASE WHEN course.certification THEN [1] ELSE [] END | SET c:Certification)