diff --git a/.vscode/settings.json b/.vscode/settings.json index 36060c712..4d647e835 100644 --- a/.vscode/settings.json +++ b/.vscode/settings.json @@ -20,5 +20,4 @@ "scheme": "file" } ], - "asciidoc.antora.enableAntoraSupport": true, } \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/course.adoc b/asciidoc/courses/genai-workshop/course.adoc new file mode 100644 index 000000000..3ba330b1b --- /dev/null +++ b/asciidoc/courses/genai-workshop/course.adoc @@ -0,0 +1,40 @@ += Gen-AI - Hands-on Workshop +:status: active +:duration: 2 hours +:caption: GenAI Beyond Chat with RAG, Knowledge Graphs and Python +:usecase: blank-sandbox +:key-points: A comma, separated, list of learnings +:repository: neo4j-graphacademy/genai-workshop + +== Course Description + +In this GenAI and Neo4j workshop, you will learn how Neo4j can support your GenAI projects. + +You will: + +* Use Vector indexes and embeddings in Neo4j to perform similarity and keyword search +* Use Python and Langchain to integrate with Neo4j and OpenAI +* Learn about Large Language Models (LLMs), hallucination and integrating knowledge graphs +* Explore Retrieval Augmented Generation (RAG) and its role in grounding LLM-generated content + +After completing this workshop, you will be able to explain the terms LLM, RAG, grounding, and knowledge graphs. You will also have the knowledge and skills to create simple LLM-based applications using Neo4j and Python. + +=== Prerequisites + +Before taking this course, you should have: + +* A basic understanding of Graph Databases and Neo4j +* Knowledge of Python and capable of reading simple programs + +While not essential, we completing the GraphAcademy link:/courses/neo4j-fundamentals/[Neo4j Fundamentals^] course. + +=== Duration + +{duration} + +== What you need + +To complete the practical tasks within this workshop, you will need: + +* Access to gitpod.io (you will need a github, gitpod, or bitbucket account) or a local Python environment +* An OpenAI billing account and API key diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/1-getting-started/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/1-getting-started/lesson.adoc new file mode 100644 index 000000000..469901a9e --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/1-getting-started/lesson.adoc @@ -0,0 +1,83 @@ += Getting Started +:order: 1 +:type: lesson +:lab: {repository-link} +: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. + +A blank Neo4j Sandbox instance has also been created for you to use during this course. + +You can open a Neo4j Browser window throughout this course by clicking the link:#[Toggle Sandbox,role=classroom-sandbox-toggle] button in the bottom right-hand corner of the screen. + +== Get the code + +You can use Gitpod as an online IDE and workspace for this workshop. +It will automatically clone the workshop repository and set up your environment. + +lab::Open `Gitpod workspace`[] + +[NOTE] +You will need to login with a Github, Gitlab, or Bitbucket account. + +Alternatively, you can clone the repository and set up the environment yourself. + +[%collapsible] +.Develop on your local machine +==== +You will need link:https://python.org[Python] installed and the ability to install packages using `pip`. + +You may want to set up a virtual environment using link:https://docs.python.org/3/library/venv.html[`venv`^] or link:https://virtualenv.pypa.io/en/latest/[`virtualenv`^] to keep your dependencies separate from other projects. + +Clone the link:https://github.com/neo4j-graphacademy/genai-workshop[github.com/neo4j-graphacademy/genai-workshop] repository: + +[source,bash] +---- +git clone https://github.com/neo4j-graphacademy/genai-workshop +---- + +Install the required packages using `pip`: + +[source,bash] +---- +cd genai-workshop +pip install -r requirements.txt +---- +==== + +== Setup the environment + +Create a copy of the `.env.example` file and name it `.env`. +Fill in the required values. + +[source] +.Create a .env file +---- +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]. + +Update the Neo4j sandbox connection details: + +NEO4J_URI:: [copy]#bolt://{sandbox_ip}:{sandbox_boltPort}# +NEO4J_USERNAME:: [copy]#{sandbox_username}# +NEO4J_PASSWORD:: [copy]#{sandbox_password}# + +== Test your setup + +You can test your setup by running `test_environment.py` - this will attempt to connect to the Neo4j sandbox and the OpenAI API. + +You will see an `OK` message if you have set up your environment correctly. If any tests fail, check the contents of the `.env` file. + +== Continue + +When you are ready, you can move on to the next task. + +read::Success - let's get started![] + +[.summary] +== Summary + +You have setup your environment and are ready to start the workshop. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/10-expand-graph/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/10-expand-graph/lesson.adoc new file mode 100644 index 000000000..0b7391184 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/10-expand-graph/lesson.adoc @@ -0,0 +1,44 @@ += Expand the Graph +:order: 10 +:type: challenge +:optional: true +:sandbox: true + +In this *optional* challenge, you can extend the graph with additional data. + +== All Courses + +Currently, the graph contains data from a single course, `llm-fundamentals`, you can download the link:https://data.neo4j.com/llm-vectors-unstructured/courses.zip[lesson files for all the courses^]. + +. Download the content for all the courses - link:https://data.neo4j.com/llm-vectors-unstructured/courses.zip[data.neo4j.com/llm-vectors-unstructured/courses.zip^] +. Update the graph with the new data +. Explore the graph and find the connections between the courses + +== Additional metadata + +While the course content is unstructured, it contains metadata you can extract and include in the graph. + +Examples include: + +* The course title is the first level 1 heading in the file - `= Course Title` +* Level 2 headings denote section titles - `== Section Title` +* The lessons include parameters in the format `:parameter: value` at the top of the file, such as: +** `:type:` - the type of lesson (e.g. `lesson`, `challenge`, `quiz`) +** `:order:` - the order of the lesson in the module +** `:optional:` - whether the lesson is optional + +Explore the course content and see what other data you can extract and include in the graph. + +When you are ready to move on, click Continue. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +In this optional challenge, you extended the graph with additional data. + diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/11-next-steps/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/11-next-steps/lesson.adoc new file mode 100644 index 000000000..3b4ee705a --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/11-next-steps/lesson.adoc @@ -0,0 +1,20 @@ += Next steps +:order: 11 +:type: lesson + +Congratulations on completing this workshop! + +You have: + +* Used vector indexes to search for similar data +* Created embeddings and vector indexes +* Built a graph of unstructured data using Python and Langchain + +You can learn more about Neo4j at link:graphacademy.neo4j.com[Neo4j GraphAcademy]. + +read::Finished[] + +[.summary] +== Summary + +Congratulations on completing this workshop! \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/3d-vector.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/3d-vector.svg new file mode 100644 index 000000000..a4fe3a616 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/3d-vector.svg @@ -0,0 +1 @@ + \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/Apple-tech-or-fruit.png b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/Apple-tech-or-fruit.png new file mode 100644 index 000000000..7816211c3 Binary files /dev/null and b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/Apple-tech-or-fruit.png differ diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/vector-distance.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/vector-distance.svg new file mode 100644 index 000000000..a29b92041 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/images/vector-distance.svg @@ -0,0 +1 @@ + \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/lesson.adoc new file mode 100644 index 000000000..64cd4a6be --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/2-vectors/lesson.adoc @@ -0,0 +1,72 @@ += Semantic Search, Vectors, and Embeddings +:order: 2 +:type: lesson + +Machine learning and natural language processing (NLP) often use vectors and embeddings to represent and understand data. + +== Semantic Search + +Semantic search aims to understand search phrases' intent and contextual meaning, rather than focusing on individual keywords. + +Traditional keyword search often depends on exact-match keywords or proximity-based algorithms that find similar words. + +For example, if you input "apple" in a traditional search, you might predominantly get results about the fruit. + +However, in a semantic search, the engine tries to gauge the context: Are you searching about the fruit, the tech company, or something else? + +image:images/Apple-tech-or-fruit.png[An apple in the middle with a tech icons on the left and a food on the right,width=700,align=center] + + +== What are Vectors + +Vectors are simply a list of numbers. +For example, the vector `[1, 2, 3]`` is a list of three numbers and could represent a point in three-dimensional space. + +image:images/3d-vector.svg[A diagram showing a 3d representation of the x,y,z coordinates 1,1,1 and 1,2,3] + +You can use vectors to represent many different types of data, including text, images, and audio. + +Using vectors with a dimensionality of hundreds and thousands in machine learning and natural language processing (NLP) is common. + +== What are Embeddings? + +When referring to vectors in the context of machine learning and NLP, the term "embedding" is typically used. +An embedding is a vector that represents the data in a useful way for a specific task. + +Each dimension in a vector can represent a particular semantic aspect of the word or phrase. +When multiple dimensions are combined, they can convey the overall meaning of the word or phrase. + +For example, the word "apple" might be represented by an embedding with the following dimensions: + +* fruit +* technology +* color +* taste +* shape + +You can create embeddings in various ways, but one of the most common methods is to use a **large language model**. + +For example, the embedding for the word "apple" is `0.0077788467, -0.02306925, -0.007360777, -0.027743412, -0.0045747845, 0.01289164, -0.021863015, -0.008587573, 0.01892967, -0.029854324, -0.0027962727, 0.020108491, -0.004530236, 0.009129008,` ... and so on. + +== How are vectors used in semantic search? + +You can use the _distance_ or _angle_ between vectors to gauge the semantic similarity between words or phrases. + +image::images/vector-distance.svg[A 3 dimensional chart illustrating the distance between vectors. The vectors are for the words "apple" and "fruit",width=700,align=center] + +Words with similar meanings or contexts will have vectors that are close together, while unrelated words will be farther apart. + +This principle is employed in semantic search to find contextually relevant results for a user's query. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned about semantic search, vectors, and embeddings. + +Next, you will use a Neo4j vector index to find similar data. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/lesson.adoc new file mode 100644 index 000000000..79cab0d96 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/lesson.adoc @@ -0,0 +1,66 @@ += Search using a Vector Index +:order: 3 +:type: challenge +:sandbox: true + +The Neo4j sandbox contains a sample of 1000 movies. +Running the following Cypher query will return the titles and plots for the movies in the database: + +[source, cypher] +---- +MATCH (m:Movie) +RETURN m.title, m.plot +---- + +Review the movies and find a plot that you think looks interesting. + +You can adapt the query to only return a named movie by adding a filter: + +[source, cypher] +---- +MATCH (m:Movie {title: "Toy Story"}) +RETURN m.title, m.plot +---- + +== Finding similar movies + +You can view the embedding for a movie plot by running the following query: + +[source, cypher] +---- +MATCH (m:Movie {title: "Toy Story"}) +RETURN m.title, m.plotEmbedding +---- + +You can find similar movies using the embedding for the movie plot and a vector index. + +You can query the vector index to find similar movies by running the following query: + +[source, cypher] +---- +MATCH (m:Movie {title: 'Toy Story'}) + +CALL db.index.vector.queryNodes('moviePlots', 6, m.plotEmbedding) +YIELD node, score + +RETURN node.title, node.plot, score +---- + +The `db.index.vector.queryNodes` procedure takes three arguments: + +* The name of the vector index to query - `moviePlots` +* The number of results to return - `6` +* The embedding to search for - `m.plotEmbedding` + +Experiment with the query to find similar movies to the one you searched earlier. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned how to use a vector index to find similar unstructured data. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/reset.cypher b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/reset.cypher new file mode 100644 index 000000000..0e71a0ba7 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/3-search-vector/reset.cypher @@ -0,0 +1,27 @@ +LOAD CSV WITH HEADERS +FROM 'https://data.neo4j.com/llm-vectors-unstructured/movies-plot-embedding.csv' AS row +MERGE (m:Movie {movieId: toInteger(row.movieId)}) +SET +m.tmdbId = toInteger(row.tmdbId), +m.imdbId = toInteger(row.imdbId), +m.released = row.released, +m.title = row.title, +m.year = toInteger(row.year), +m.plot = row.plot, +m.budget = toInteger(row.budget), +m.imdbRating = toFloat(row.imdbRating), +m.poster = row.poster, +m.runtime = toInteger(row.runtime), +m.imdbVotes = toInteger(row.imdbVotes), +m.revenue = toInteger(row.revenue), +m.url = row.url +WITH m, row +CALL db.create.setNodeVectorProperty(m, 'plotEmbedding', apoc.convert.fromJsonList(row.plotEmbedding)); + +CREATE VECTOR INDEX moviePlots IF NOT EXISTS +FOR (m:Movie) +ON m.plotEmbedding +OPTIONS {indexConfig: { + `vector.dimensions`: 1536, + `vector.similarity_function`: 'cosine' +}}; \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/4-embeddings/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/4-embeddings/lesson.adoc new file mode 100644 index 000000000..06ac57901 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/4-embeddings/lesson.adoc @@ -0,0 +1,86 @@ += Creating Embeddings +:order: 4 +:type: challenge +:sandbox: true + + +In this task, you will use Cypher and Python to create embeddings. + +== Find a movie plot + +In the previous task, you used a vector index to find similar movies. + +To find a movie with a plot you define, you need to create an embedding for your text before you can query the vector index. + +For example, to find a movie about "A mysterious spaceship lands Earth", you need to: + +. Create an embedding for the text "A mysterious spaceship lands Earth". +. Pass the embedding to the `db.index.vector.queryNodes` function. + +You can generate a new embedding in Cypher using the link:https://neo4j.com/docs/cypher-manual/current/genai-integrations/#single-embedding[`genai.vector.encode`^] function: + +For example, you can use the `OpenAI` provider to generate an embedding passing the API key as `token` in the `configuration` map: + +[source, cypher] +---- +WITH genai.vector.encode("Text to create embeddings for", "OpenAI", { token: "sk-..." }) AS embedding +RETURN embedding +---- + +[IMPORTANT] +Remember to replace `sk-...` with your OpenAI API key. + +You can use the embedding to query the vector index to find similar movies. + +[source, cypher] +---- +WITH genai.vector.encode( + "A mysterious spaceship lands Earth", + "OpenAI", + { token: "sk-..." }) AS myMoviePlot +CALL db.index.vector.queryNodes('moviePlots', 6, myMoviePlot) +YIELD node, score +RETURN node.text, score +---- + +Experiment with different movie plots and observe the results. + +=== OpenAI API + +You can also use the OpenAI API to create embeddings using Python. + +Open the `1-knowledge-graphs-vectors\create_embeddings.py` file in the code editor. + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/create_embeddings.py[create] + +---- + +Review the code before running it and note that: + +- `load_dotenv()` loads the environment variables from the `.env` file. +- `OpenAI()` creates an instance of the OpenAI class. +- `llm.embeddings.create()` creates an embedding for the input text using the `text-embedding-ada-002` model. +- The response containing the embeddings is printed to the console. + +Run the code. +You should see a list of numbers representing the embedding: + +[source] +---- +[-0.028445715084671974, 0.009996716864407063, 0.0017208183417096734, -0.010130099952220917, ...] +---- + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned how to create embeddings using Cypher and Python. + +In the next task, you will learn how to create a vector index on an embedding. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/images/babe-similar-posters.jpg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/images/babe-similar-posters.jpg new file mode 100644 index 000000000..f551d595f Binary files /dev/null and b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/images/babe-similar-posters.jpg differ diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/lesson.adoc new file mode 100644 index 000000000..a0ff16190 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/lesson.adoc @@ -0,0 +1,120 @@ += Create a Vector Index +:order: 5 +:type: challenge +:sandbox: true + +Your next task is to create a vector index using Cypher. + +You previously used a vector index to find similar text; you can also use a vector index to find similar images. + +== Movie posters + +GraphAcademy has loaded a dataset of movie posters into the sandbox. +Each movie has a URL to a poster image: + +[source, cypher] +MATCH (m:Movie {title: "Toy Story"}) +RETURN m.title, m.poster + +image:https://image.tmdb.org/t/p/w440_and_h660_face/uXDfjJbdP4ijW5hWSBrPrlKpxab.jpg[Toy Story movie poster,width=250,align=center] + +The data also contains embeddings for each poster: + +[source, cypher] +MATCH (m:Movie {title: "Toy Story"}) +RETURN m.title, m.posterEmbedding + +== Create a vector index + +To search the movie poster embeddings, you must create a vector index. +Review the following Cypher to create the vector index before running it: + +[source, cypher] +---- +CREATE VECTOR INDEX moviePosters IF NOT EXISTS +FOR (m:Movie) +ON m.posterEmbedding +OPTIONS {indexConfig: { + `vector.dimensions`: 512, + `vector.similarity_function`: 'cosine' +}} +---- + +You should note the following about the index: + +- It is named `moviePosters` +- It is against the `posterEmbedding` properties on `Movie` nodes +- The vector has `512` dimensions +- The function used to compare vectors is `cosine` + +[%collapsible] +.More about dimensions +==== +The model used to create the embeddings determines the number of dimensions in the vector. + +In this case, we used the link:https://openai.com/research/clip[OpenAI Clip Model^], which has 512 dimensions. + +We created the movie plot embeddings using link:https://platform.openai.com/docs/guides/embeddings/embedding-models[Open AI's text-embedding-ada-002 model^], which has 1536 dimensions. +==== + +Run the Cypher to create the vector index. + +Check that you created the index successfully using the `SHOW INDEXES` command. + +.Show Indexes +[source,cypher] +---- +SHOW VECTOR INDEXES +---- + +You should see a result similar to the following: + +.Show Indexes Result +|=== +| id | name | state | populationPercent | type +|4 | "moviePosters" | "ONLINE" | `100.0` | "VECTOR" +|=== + +Once the `state` is listed as "ONLINE", the index will be ready to query. + +The `populationPercentage` field indicates the proportion of node and property pairing. +When the `populationPercentage` is `100.0`, all the movie embeddings have been indexed. + +== Similar posters + +You can use the `db.index.vector.queryNodes` procedure to find similar movie posters. + +[source, cypher] +---- +MATCH (m:Movie{title: "Babe"}) + +CALL db.index.vector.queryNodes('moviePosters', 6, m.posterEmbedding) +YIELD node, score + +RETURN node.title, node.poster, score; +---- + +image:images/babe-similar-posters.jpg[3 movie posters, Babe, Lassie, Before the Rain with similar images,width=700,align=center] + +Pick a different movie and write a similar Cypher query to find similar posters. + +You can view all the movie titles using this Cypher: + +[source, cypher] +---- +MATCH (m:Movie) +RETURN m.title +---- + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned how to create a vector index in Neo4j. + +Next, you will learn how to model unstructured data as a graph. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/reset.cypher b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/reset.cypher new file mode 100644 index 000000000..27dbd8559 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/5-create-vector-index/reset.cypher @@ -0,0 +1,19 @@ +LOAD CSV WITH HEADERS +FROM 'https://data.neo4j.com/llm-vectors-unstructured/movies-poster-embedding.csv' AS row +MERGE (m:Movie {movieId: toInteger(row.movieId)}) +SET +m.tmdbId = toInteger(row.tmdbId), +m.imdbId = toInteger(row.imdbId), +m.released = row.released, +m.title = row.title, +m.year = toInteger(row.year), +m.plot = row.plot, +m.budget = toInteger(row.budget), +m.imdbRating = toFloat(row.imdbRating), +m.poster = row.poster, +m.runtime = toInteger(row.runtime), +m.imdbVotes = toInteger(row.imdbVotes), +m.revenue = toInteger(row.revenue), +m.url = row.url +WITH m, row +CALL db.create.setNodeVectorProperty(m, 'posterEmbedding', apoc.convert.fromJsonList(row.posterEmbedding)); \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/images/graphacademy-lessons-paragraph.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/images/graphacademy-lessons-paragraph.svg new file mode 100644 index 000000000..8962d9db1 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/images/graphacademy-lessons-paragraph.svg @@ -0,0 +1 @@ +HAS_MODULEHAS_LESSONCONTAINSCoursename:url:Modulename:order:url:Lessonname:order:text:url:Paragraphtext:embedding: \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/lesson.adoc new file mode 100644 index 000000000..aac11fab8 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/6-unstructured-data/lesson.adoc @@ -0,0 +1,43 @@ += Unstructured data +:order: 6 +:type: lesson + +Unstructured data refers to information that doesn't fit neatly into pre-defined structures and types. +For example, text files, emails, social media posts, videos, photos, audio files, and web pages. + +Unstructured data is often rich in information but challenging to analyze. + +== Vectors and Graphs + +Vectors and embeddings can represent unstructured data, making it easier to identify similarities and search for related data. + +Graphs are a powerful tool for representing and analyzing unstructured data. + +For example, you can use vectors to find the correct documentation to support a customer query and a graph to understand the relationships between different products and customer feedback. + +== Chunking + +When dealing with large amounts of data, breaking it into smaller, more manageable chunks is helpful. This process is called chunking. + +There are countless strategies for splitting data into chunks, and the best approach depends on the data and the problem you are trying to solve. + +Later in this workshop, you will import the unstructured data from GraphAcademy course and chunk it into paragraphs. + +You can store embeddings for individual chunks and create relationships between chunks to capture context and relationships. + +When storing the course content, you will create a node for each `Paragraph` chunk and a relationship `CONTAINS` between the `Lesson` and `Paragraph` nodes. + +image::images/graphacademy-lessons-paragraph.svg[A graph showing lesson and chunk nodes. Connected by `CONTAINS` relationship,width=700,align=center] + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned about how you can store unstructured data in a graph. + +In the next task, you will use Python and Langchain to load, chunk, embed, and store unstructured data in Neo4j. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/7-import-unstructured-data/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/7-import-unstructured-data/lesson.adoc new file mode 100644 index 000000000..eaf5fb758 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/7-import-unstructured-data/lesson.adoc @@ -0,0 +1,153 @@ += Import Unstructured Data +:order: 7 +:type: challenge +:sandbox: true + +You will use Python and Langchain to chunk up course content and create embeddings for each chunk. +You will then load the chunks into a Neo4j graph database. + + +== The course content + +You will load the content from the course link:https://graphacademy.neo4j.com/courses/llm-fundamentals/[Neo4j & LLM Fundamentals^]. + +The workshop repository you cloned contains the course data. + +Open the `1-knowledge-graphs-vectors\data` directory in your code editor. + +You should note the following structure: + +* `asciidoc` - contains the course content in ascidoc format +** `courses` - the course content +*** `llm-fundamentals` - the course name +**** `modules` - contains numbered directories for each module +***** `01-name` - the module name +****** `lessons` - contains numbered directories for each lesson +******* `01-name` - the lesson name +******** `lesson.adoc` - the lesson content + +== Load the content and chunk it + +You will load the content and chunk it using Python and Langchain. + +Your code will split the lesson content into chunks of text, around 1500 characters long, each containing one or more paragraphs. +You can determine the paragraph in the content with two newline characters (`\n\n`). + +Open the `1-knowledge-graphs-vectors/create_vector.py` file and review the program: + +[source,python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/create_vector.py[] +---- + +The program uses the link:https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.directory.DirectoryLoader.html[`DirectoryLoader`^] class to load the content from the `data/asciidoc` directory. + +Your task is to add the code to: + +. Create a link:https://api.python.langchain.com/en/latest/text_splitter/langchain.text_splitter.CharacterTextSplitter.html[`CharacterTextSplitter`^] object to split the content into chunks of text. +. Use the `split_documents` method to split the documents into chunks of text based on the existence of `\n\n` and a chunk size of 1500 characters. + +Create the CharacterTextSplitter object to split the content into paragraphs (`\n\n`). + +[source,python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/create_vector.py[tag=splitter] +---- + +Split the documents into chunks of text. + +[source,python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/create_vector.py[tag=split] +---- + +[TIP] +You can run your code now to see the chunks of text. + +[%collapsible] +.More on splitting +==== +The content isn't split simply by a character (`\n\n`) or on a fixed number of characters. +The process is more complicated. +Chunks should be up to maximum size but conform to the character split. + +In this example, the `split_documents` method does the following: + +. Splits the documents into paragraphs (using the `separator` - `\n\n`) +. Combines the paragraphs into chunks of text that are up 1500 characters (`chunk_size`) +** if a single paragraph is longer than 1500 characters, the method will not split the paragraph but create a chunk larger than 1500 characters +. Adds the last paragraph in a chunk to the start of the next paragraph to create an overlap between chunks. +** if the last paragraph in a chunk is more than 200 characters (`chunk_overlap`) it will *not* be added to the next chunk + +This process ensures that: + +* Chunks are never too small. +* That a paragraph is never split between chunks. +* That chunks are significantly different, and the overlap doesn't result in a lot of repeated content. + +Investigate what happens when you modify the `separator`, `chunk_size` and `chunk_overlap` parameters. +==== + +== Create vector index + +Once you have chunked the content, you can use the Langchain link:https://python.langchain.com/docs/integrations/vectorstores/neo4jvector[`Neo4jVector`^] class to create embeddings, a vector index, and store the chunks in a Neo4j graph database. + +Modify your Python program to include the following code: + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/create_vector.py[tag=vector] +---- + +The code will create 'Chunk' nodes with `text` and `embedding` properties and a vector index called `chunkVector`. +You should be able to identify where you pass the `Chunk`, `text`, `embedding`, and `chunkVector` parameters. + +[%collapsible] +.View the complete code +==== +[source] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/create_vector.py[] +---- +==== + +Run the program to create the chunk nodes and vector index. It may take a minute or two to complete. + +== View chunks in the sandbox + +You can now view the chunks in the Neo4j sandbox. + +[source,cypher] +---- +MATCH (c:Chunk) RETURN c LIMIT 25 +---- + +You can also query the vector index to find similar chunks. +For example, you can find lesson chunks relating to a specific question, "What does Hallucination mean?": + +[source,cypher] +---- +WITH genai.vector.encode( + "What does Hallucination mean?", + "OpenAI", + { token: "sk-..." }) AS userEmbedding +CALL db.index.vector.queryNodes('chunkVector', 6, userEmbedding) +YIELD node, score +RETURN node.text, score +---- + +[IMPORTANT] +Remember to replace `sk-...` with your OpenAI API key. + +Experiment with different questions and see how the vector index can find similar chunks. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned to use Python and Langchain to load, chunk, and vectorize unstructured data into a Neo4j graph database. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/generic-knowledge-graph.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/generic-knowledge-graph.svg new file mode 100644 index 000000000..1d672273d --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/generic-knowledge-graph.svg @@ -0,0 +1 @@ +sourcesourcesourcesourcesourcesourceaboutaboutaboutrelates toSourceAchunk1chunk2chunk3SourceBchunk4chunk5chunk6topic itopic j \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/neo4j-google-knowledge-graph.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/neo4j-google-knowledge-graph.svg new file mode 100644 index 000000000..b3e6ed35c --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/images/neo4j-google-knowledge-graph.svg @@ -0,0 +1 @@ +FOUNDEDLOCATEDLOCATEDCAPITAL_OFFOUNDERWORKS_ATABOUTWRITTEN_BYOWNER_OFPUBLISHED ONREFERS_TOPUBLISHED_ONNeo4jCompanyMalmoLocationLondonLocationBlogPostArticleUnitedKingdomLocationEmilEifrémPersonneo4j.comWebsiteDatabaseTechnologyDocumentationArticle \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/lesson.adoc new file mode 100644 index 000000000..114677a71 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/8-knowledge-graph/lesson.adoc @@ -0,0 +1,46 @@ += Knowledge graph +:order: 8 +:type: lesson + +Knowledge graphs are essential to many AI and machine learning applications. +You can use a knowledge graph to give context and ground an LLM, giving it access to structured data beyond its initial training data. + +== What are Knowledge Graphs? + +Knowledge graphs are a specific implementation of a Graph Database, where information is captured and integrated from many different sources, representing the inherent knowledge of a particular domain. + +They provide a structured way to represent entities, their attributes, and their relationships, allowing for a comprehensive and interconnected understanding of the information within that domain. + +Knowledge graphs break down sources of information and integrate them, allowing you to see the relationships between the data. + +image::images/generic-knowledge-graph.svg[a diagram of an abstract knowledge graph showing how sources contain chunks of data about topics which can be related to other topics] + +You can tailor knowledge graphs for semantic search, data retrieval, and reasoning. + +You may not be familiar with the term knowledge graph, but you have probably used one. Search engines typically use knowledge graphs to provide information about people, places, and things. + +The following knowledge graph could represent Neo4j: + +image::images/neo4j-google-knowledge-graph.svg[An example of a knowledge graph of Neo4j showing the relationships between people, places, and things] + +This integration from diverse sources gives knowledge graphs a more holistic view and facilitates complex queries, analytics, and insights. + +[TIP] +You can find more information about knowledge graphs including white papers, and free resources at link:https://neo4j.com/use-cases/knowledge-graph[neo4j.com/use-cases/knowledge-graph^]. + +Knowledge graphs can readily adapt and evolve as they grow, taking on new information and structure changes. + +In the next task, you will build a simple graph of the course data. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] + +[.summary] +== Summary + +You learned about knowledge graphs and their benefits. + +In the next task, you will build a simple graph of the course data. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/course-graph-result.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/course-graph-result.svg new file mode 100644 index 000000000..ca033110b --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/course-graph-result.svg @@ -0,0 +1,7 @@ +Neo4j Graph VisualizationCreated using Neo4j (http://www.neo4j.com/)HAS_MODULEHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_MODULEHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_MODULEHAS_LESSONCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSHAS_MODULEHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINSCONTAINSHAS_LESSONCONTAINSCONTAINS llm-fund… Cypher gener… 3-groun… 1-introdu… If your prompt sugg This approach is kn = Grounding LLM… image::i… 2-halluci… Providing… You could also incl Luckily,wh… On the other… = Avoiding Hall… The combi… 1-neo4j-… LLMs are fine-tu… Precision in the ta Knowled… They provide a stru = Introd… read::Co… 4-improv… 2-vector… When a user asks a By leveraging the c = Improving Se… The similarity scor 2-vector-… Run the query. The You canpr… You shouldre… Note that in… You can link:htt… .Loading the Em… [source,… = Vector Index… image::i… 1-seman… Semantic search sys Each dimension in a = Vectors Se… # Append the toolt… 7-c-neo4… 3-intro-t… = Adding theNe… By incorp… 6-retriev… `page_c… [source,… = Retrie… [TIP] .Refre… 5-conne… 'url', 'type': 'STR [source,… You can access the = Conne… However, when asked 4-agents [source, bash] +… The `Agent… Agents support mult In addition to the [source,… = Agent… state.ad… 3.5-mem… [source,--… [source,--… = Giving a Chat Mod Investig… 3-chat-m… Currently… --- + +inclu… [source,… = Chat Model… alones inap… 2.5-chains Setting the `out… = Chain… == Check YourUn… 2-initialis… [NOTE] .Differing R Modify your pro… That `OpenAI` is us == Setup +… = Initialising the == Check YourUn… 1-langch… **Model Intera… = An introd… read::Co… 9-conver… 4-cypher… = Conve… Which returns the c 7-fewsh… Example… = Few + +shot Exa… MATCH (m:Movie {tit 5-specifi… Who acted inMa… Instructi… = Providing Spe… == Check YourUn… 1-cypher… Experim… . The program insta The programw… = The CypherCh… \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/graphacademy-simple-graph.svg b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/graphacademy-simple-graph.svg new file mode 100644 index 000000000..131fc243e --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/images/graphacademy-simple-graph.svg @@ -0,0 +1 @@ +HAS_MODULEHAS_LESSONCONTAINSCoursename:Modulename:Lessonname:url:Paragraphtext:embedding: \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/lesson.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/lesson.adoc new file mode 100644 index 000000000..879af6f34 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/lessons/9-build-graph/lesson.adoc @@ -0,0 +1,202 @@ += Build Graph +:order: 9 +:type: challenge +:sandbox: true + + +In the previous task, you used the `Neo4jVector` class to create nodes in the graph. +Using `Neo4jVector` is an efficient and easy way to get started. + +To create a graph where you can also understand the relationships within the data, you must incorporate the metadata into the data model. + +In this lesson, you will create a graph of the course content using the `neo4j` Python driver and OpenAI API. + +== Data Model + +The data model you will create is a simplified version of the course content model you saw earlier. + +image::images/graphacademy-simple-graph.svg[Data model showing Course, Module, Lesson and Paragraph nodes and their relationships,width=700,align=center] + +The graph will contain the following nodes, properties, and relationships: + +- `Course`, `Module`, and `Lesson` nodes with a `name` property +- A `url` property on `Lesson` nodes will hold the GraphAcademy URL for the lesson +- `Paragraph` nodes will have `text` and `embedding` property +- The `HAS_MODULE`, `HAS_LESSON`, and `CONTAINS` relationships will connect the nodes + +You can extract the `name` properties and `url` metadata from the directory structure of the lesson files. +For example, the first lesson of the Neo4j & LLM Fundamentals course has the following path: + +[source] +---- +courses\llm-fundamentals\modules\1-introduction\lessons\1-neo4j-and-genai\lesson.adoc +---- + +You can extract the following metadata from the path: + +- `Course.name` - `llm-fundamentals` +- `Module.name` - `1-introduction` +- `Lesson.name` - `1-neo4j-and-genai` +- `Lesson.url` - `graphacademy.neo4j.com/courses/{Course.name}/{{Module.name}}/{Lesson.name}` + +== Extracting the data + +Open the `1-knowledge-graphs-vectors\build_graph.py` file in your code editor. + +This starter code loads and chunks the course content. + +.Load and chunk the content +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/build_graph.py[] +---- + +For each chunk, you have to create an embedding of the text and extract the metadata. + +Create a function to create and return an embedding using the OpenAI API: + +.Create embeddings +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=get_embedding] +---- + +Create a 2nd function, which will extract the data from the chunk: + +.Get course data +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=get_course_data] +---- + +The `get_course_data` function: + +. Splits the document source path to extract the `course`, `module`, and `lesson` names +. Constructs the `url` using the extracted names +. Extracts the `text` from the chunk +. Creates an `embedding` using the `get_embedding` function +. Returns a dictionary containing the extracted data + +== Create the graph + +To create the graph, you will need to: + +. Create an OpenAI object to generate the embeddings +. Connect to the Neo4j database +. Iterate through the chunks +. Extract the course data from each chunk +. Create the nodes and relationships in the graph + +Create the OpenAI object: + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=openai] +---- + +Connect to the Neo4j sandbox: + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=neo4j] +---- + +[TIP] +.Test the connection +==== +You could run your code now to check that you can connect to the OpenAI API and Neo4j sandbox. +==== + +To create the data in the graph, you will need a function that incorporates the course data into a Cypher statement and runs it in a transaction. + +.Create chunk function +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=create_chunk] +---- + +The `create_chunk` function will accept the `data` dictionary created by the `get_course_data` function. + +You should be able to identify the `$course`, `$module`, `$lesson`, `$url`, `$text`, and `$embedding` parameters in the Cypher statement. + +Iterate through the chunks and execute the `create_chunk` function: + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=create] +---- + +A new session is created for each chunk. The `execute_write` method calls the `create_chunk` function, passing the `data` dictionary created by the `get_course_data` function. + +Finally, close the driver. + +[source, python] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[tag=close] +---- + +[%collapsible] +.Click to view the complete code +==== +[source] +---- +include::{repository-raw}/main/1-knowledge-graphs-vectors/solutions/build_graph.py[] +---- +==== + +== Explore the graph + +Run the code to create the graph. +It will take a minute or two to complete as it creates the embeddings for each paragraph. + +View the graph by running the following Cypher: + +[source, cypher] +---- +MATCH (c:Course)-[:HAS_MODULE]->(m:Module)-[:HAS_LESSON]->(l:Lesson)-[:CONTAINS]->(p:Paragraph) +RETURN * +---- + +image::images/course-graph-result.svg[Result from the Cypher, a graph showing Course, Module, Lesson and Chunk nodes and their relationships,width=700,align=center] + + +You will need to create a vector index to query the paragraph embeddings. + +[source, cypher] +.Create Vector Index +---- +CREATE VECTOR INDEX paragraphs IF NOT EXISTS +FOR (p:Paragraph) +ON p.embedding +OPTIONS {indexConfig: { + `vector.dimensions`: 1536, + `vector.similarity_function`: 'cosine' +}} +---- + +You can use the vector index and the graph to find a lesson to help with specific questions: + +[source, cypher] +.Find a lesson +---- +WITH genai.vector.encode( + "How does RAG help ground an LLM?", + "OpenAI", + { token: "sk-..." }) AS userEmbedding +CALL db.index.vector.queryNodes('paragraphs', 6, userEmbedding) +YIELD node, score +MATCH (l:Lesson)-[:CONTAINS]->(node) +RETURN l.name, l.url, score +---- + +Explore the graph and see how the relationships between the nodes can bring additional meaning to the unstructured data. + +== Continue + +When you are ready, you can move on to the next task. + +read::Move on[] +[.summary] +== Summary + +You created a graph of the course content using the `neo4j` Python driver and OpenAI API. \ No newline at end of file diff --git a/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/module.adoc b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/module.adoc new file mode 100644 index 000000000..021585163 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/1-knowledge-graphs-vectors/module.adoc @@ -0,0 +1,20 @@ += Knowledge Graphs, Unstructured Data, and Vectors +:order: 1 + +== Workshop Overview + +In this workshop, you will: + +* Use vector indexes to search for similar data +* Create embeddings and vector indexes +* Build a graph of unstructured data using Python and Langchain + +== Workshop Structure + +This workshop is hands-on, and you will be writing code. + +Each section will have a brief introduction, followed by a practical activity. + +If you are ready, let's get going! + +link:./1-getting-started/[Ready? Let's go →, role=btn] diff --git a/asciidoc/courses/genai-workshop/modules/2-llm-rag-python-langchain/module.adoc b/asciidoc/courses/genai-workshop/modules/2-llm-rag-python-langchain/module.adoc new file mode 100644 index 000000000..037b68676 --- /dev/null +++ b/asciidoc/courses/genai-workshop/modules/2-llm-rag-python-langchain/module.adoc @@ -0,0 +1,4 @@ += LLMs, RAG, Python, and Langchain +:order: 2 + +COMING SOON \ No newline at end of file