docs: adds model name virtualization page#856
Merged
Conversation
Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com>
Contributor
There was a problem hiding this comment.
Pull Request Overview
Adds a new documentation page for model name virtualization and updates the provider fallback page with frontmatter metadata.
- Introduces a “Model Name Virtualization” guide detailing the
modelNameOverridefield for routing - Provides YAML examples for both split-traffic and fallback scenarios
- Adds frontmatter to
fallback.mdto integrate it into the sidebar
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| site/docs/capabilities/traffic/model-virtualization.md | New doc covering modelNameOverride use cases and examples |
| site/docs/capabilities/traffic/fallback.md | Added page metadata (id, title, sidebar_position) for fallback |
Comments suppressed due to low confidence (2)
site/docs/capabilities/traffic/model-virtualization.md:10
- [nitpick] Consider adding an explicit H1 page title (e.g.,
# Model Name Virtualization) after the frontmatter to match other docs and improve page structure.
Envoy AI Gateway provides an advanced model name virtualization capability that allows you to manage and route requests to different AI models seamlessly.
site/docs/capabilities/traffic/model-virtualization.md:79
- It may be helpful to add a note clarifying that the first backendRef without a
modelNameOverridewill use the original model name (gpt-4) from the header to avoid confusion.
- name: openai-backend
aabchoo
reviewed
Jul 10, 2025
missBerg
approved these changes
Jul 10, 2025
Member
Author
|
Thanks for the look you two! |
alexagriffith
pushed a commit
to sukumargaonkar/ai-gateway
that referenced
this pull request
Jul 11, 2025
**Description** This adds model name virtualization page that describes a cool "modelNameOveride" API and how it can be used for multiple use cases. **Related Issues/PRs (if applicable)** Closes envoyproxy#846 --------- Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net>
alexagriffith
added a commit
to sukumargaonkar/ai-gateway
that referenced
this pull request
Jul 11, 2025
Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> use anthropic default const Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> add helper methods Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> add lower bound temp test Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> make new tool helper and add/fix test Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> validate json schema/ helper Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> remove unused var Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> update return Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> add util tests Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> test: refactors testupstream_test setup in e2e (envoyproxy#853) **Description** This refactors some old tech debt during the e2e test setup. Previously, Testupstream werw defined in case-specific yamls across everywhere except that testupstream_test.yaml test case. Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> ci: commits to main pushes image/helm with sha suffix (envoyproxy#852) **Description** Replacing `latest` suffix for helm charts and docker image. Replacing suffix with commit message. **Related Issues/PRs (if applicable)** --------- Signed-off-by: Aaron Choo <achoo30@bloomberg.net> ci: fixes docker_build_job.yaml for latest push (envoyproxy#855) **Description** Follow up on envoyproxy#852 Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> docs: adds model name virtualization page (envoyproxy#856) **Description** This adds model name virtualization page that describes a cool "modelNameOveride" API and how it can be used for multiple use cases. **Related Issues/PRs (if applicable)** Closes envoyproxy#846 --------- Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> test: increase the GCP credential coverage (envoyproxy#858) ci: drops EG v1.4 from e2e target (envoyproxy#859) **Description** Since the next EG v1.5 will be our target version that AIGW v0.3 will be based on, there's no reason to keep it at the moment. This is mainly to unblock the incoming feature patches that will rely on v1.5 feature, such as envoyproxy#823. Signed-off-by: Takeshi Yoneda <t.y.mathetake@gmail.com> docs: change from Open AI to OpenAI (envoyproxy#866) **Description** This fixes "Open AI" to "OpenAI" in the documentation. Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Update util_test.go Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> Update util_test.go Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> remove comments Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This adds model name virtualization page that describes a cool "modelNameOveride" API and how it can be used for multiple use cases.
Related Issues/PRs (if applicable)
Closes #846