-
Notifications
You must be signed in to change notification settings - Fork 4.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Adding Notebook for RAG Blog #10661
Adding Notebook for RAG Blog #10661
Conversation
Signed-off-by: Abraham Omorogbe <[email protected]>
Documentation preview for e531539 will be available here when this CircleCI job completes successfully. More info
|
We'll need to update a few entries in some other files so that this notebook can be rendered as html.
LMK if you'd prefer me to push those changes to this branch or not. |
@BenWilson2 can you help me push the changes. Some of the code in Databricks specfic, so it might not need a card in MLflow. The blog will host it |
Signed-off-by: Ben Wilson <[email protected]>
Signed-off-by: Ben Wilson <[email protected]>
Signed-off-by: Ben Wilson <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Left a few minor comments, otherwise LGTM!
"texts = text_splitter.split_documents(documents)\n", | ||
"\n", | ||
"llm = Databricks(\n", | ||
" endpoint_name=\"test-endpoint-abraham-omor\",\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
" endpoint_name=\"test-endpoint-abraham-omor\",\n", | |
" endpoint_name=\"<your-endpoint-name>\",\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ah good catch. Missed that one!
} | ||
}, | ||
"source": [ | ||
"## Create an eval dataset (Golden Dataset)" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It would be helpful to have some description on what we evaluate on this dataset (relevance + latency), and why questions only are sufficient for these metrics.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agreed. I'll add some context to these main sections just so there's something to follow along with.
" list_of_documents = loader.load()\n", | ||
" text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=0)\n", | ||
" docs = text_splitter.split_documents(list_of_documents)\n", | ||
" embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
" embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n", | |
" embedding_function = DatabricksEmbeddings(endpoint=\"databricks-bge-large-en\")\n", |
For consistency
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good catch
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I left a comment in the cell above (going to push soon) that explains why this is different from above so that users can see the difference in the output results between the different embeddings models.
Signed-off-by: Ben Wilson <[email protected]>
Signed-off-by: Abraham Omorogbe <[email protected]> Signed-off-by: Ben Wilson <[email protected]> Co-authored-by: Ben Wilson <[email protected]>
Signed-off-by: Abraham Omorogbe <[email protected]> Signed-off-by: Ben Wilson <[email protected]> Co-authored-by: Ben Wilson <[email protected]>
Signed-off-by: Abraham Omorogbe <[email protected]> Signed-off-by: Ben Wilson <[email protected]> Co-authored-by: Ben Wilson <[email protected]>
🛠 DevTools 🛠
Install mlflow from this PR
Checkout with GitHub CLI
Related Issues/PRs
#xxxWhat changes are proposed in this pull request?
Add an end to end example notebook for running evaluation on a RAG application
How is this PR tested?
Does this PR require documentation update?
Release Notes
Is this a user-facing change?
What component(s), interfaces, languages, and integrations does this PR affect?
Components
area/artifacts
: Artifact stores and artifact loggingarea/build
: Build and test infrastructure for MLflowarea/deployments
: MLflow Deployments client APIs, server, and third-party Deployments integrationsarea/docs
: MLflow documentation pagesarea/examples
: Example codearea/model-registry
: Model Registry service, APIs, and the fluent client calls for Model Registryarea/models
: MLmodel format, model serialization/deserialization, flavorsarea/recipes
: Recipes, Recipe APIs, Recipe configs, Recipe Templatesarea/projects
: MLproject format, project running backendsarea/scoring
: MLflow Model server, model deployment tools, Spark UDFsarea/server-infra
: MLflow Tracking server backendarea/tracking
: Tracking Service, tracking client APIs, autologgingInterface
area/uiux
: Front-end, user experience, plotting, JavaScript, JavaScript dev serverarea/docker
: Docker use across MLflow's components, such as MLflow Projects and MLflow Modelsarea/sqlalchemy
: Use of SQLAlchemy in the Tracking Service or Model Registryarea/windows
: Windows supportLanguage
language/r
: R APIs and clientslanguage/java
: Java APIs and clientslanguage/new
: Proposals for new client languagesIntegrations
integrations/azure
: Azure and Azure ML integrationsintegrations/sagemaker
: SageMaker integrationsintegrations/databricks
: Databricks integrationsHow should the PR be classified in the release notes? Choose one:
rn/none
- No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" sectionrn/breaking-change
- The PR will be mentioned in the "Breaking Changes" sectionrn/feature
- A new user-facing feature worth mentioning in the release notesrn/bug-fix
- A user-facing bug fix worth mentioning in the release notesrn/documentation
- A user-facing documentation change worth mentioning in the release notes