Skip to content

(EAI-995): add guardrail #755

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

Merged
merged 39 commits into from
Jun 6, 2025
Merged

(EAI-995): add guardrail #755

merged 39 commits into from
Jun 6, 2025

Conversation

mongodben
Copy link
Collaborator

@mongodben mongodben commented May 29, 2025

Jira: https://jira.mongodb.org/browse/EAI-995

Changes

Notes

@mongodben mongodben marked this pull request as ready for review June 4, 2025 15:49
Copy link
Collaborator

@nlarew nlarew left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM - few small things but nothing blocking

Comment on lines +42 to +48
test("should return guardrail results", async () => {
expect(await userMessageMongoDbGuardrail(mockInput)).toMatchObject({
metadata: { type: "valid" },
rejected: false,
reason: mockGuardrailResult.reasoning,
} satisfies InputGuardrailResult);
});
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just making sure you only intended for there to be one test case in this file

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yea, just a smoke test

Comment on lines 18 to 19
const name = "extract_mongodb_metadata";
const description = "Extract MongoDB-related metadata from a user message";
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: Is there a reason to have these as separate/top level variables? We only use them in once spot and they're pretty generic names. It isn't super clear unless you scroll down that they're the name & description of the specific guardrail.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

doubt it. can adjust

@@ -192,18 +200,44 @@ export function makeGenerateResponseWithSearchTool<
}
try {
// Transform filtered references to include the required title property
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure if this comment is actually meant for the streamed references on the next line?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i think was vestige. no longer needed

@mongodben mongodben merged commit 723429e into retrieval_tool_call Jun 6, 2025
1 check was pending
@mongodben mongodben deleted the EAI-995 branch June 6, 2025 20:47
mongodben added a commit that referenced this pull request Jun 11, 2025
* (EAI-988): Refactor `GenerateResponse` for tool call support  (#687)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* (EAI-989): Refactor verified answers to wrap `GenerateResponse` (#688)

verified answer generate response

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* handle streaming

* separate generateresponse

* typo fix

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* (EAI-990): Refactor search as a tool  (#705)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* get started

* nominally working generate res w/ search

* small refactors

* aint pretty but fully functional

* hacky if more functional

* more hack

* tools

* functional if not pretty

* Add processing

* working tool calling

* making progress

* keepin on

* Clean config

* working e2e

* update model version

* Remove no longer used stuff

* decouple search results for references and whats shown to model

* fix scripts build errs

* fix broken tests

* update default ref links

* fix broken tests

* Apply suggestions from code review

Co-authored-by: Nick Larew <nick.larew@mongodb.com>

* revert default reference links

* adding missing test

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>
Co-authored-by: Nick Larew <nick.larew@mongodb.com>

* (EAI-992): Remove `ChatLlm` (#751)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* get started

* nominally working generate res w/ search

* small refactors

* aint pretty but fully functional

* hacky if more functional

* more hack

* tools

* functional if not pretty

* Add processing

* working tool calling

* making progress

* keepin on

* Clean config

* working e2e

* update model version

* Remove no longer used stuff

* decouple search results for references and whats shown to model

* fix scripts build errs

* remove ChatLlm

* lite fixes

* Remove stub

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* (EAI-993): deprecate framework (#752)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* get started

* nominally working generate res w/ search

* small refactors

* aint pretty but fully functional

* hacky if more functional

* more hack

* tools

* functional if not pretty

* Add processing

* working tool calling

* making progress

* keepin on

* Clean config

* working e2e

* update model version

* Remove no longer used stuff

* decouple search results for references and whats shown to model

* fix scripts build errs

* fix broken tests

* deprecation

* build out docs following last week convo

* clean up spec + contact

* fix merge funk

* docs updates

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* (EAI-1071): Fix broken Atlas OpenAPI ingest (#765)

* update to fix broken test

* Update packages/ingest-mongodb-public/src/sources/snooty/snootyAstToOpenApiSpec.ts

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* (EAI-995): add guardrail (#755)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* get started

* nominally working generate res w/ search

* small refactors

* aint pretty but fully functional

* hacky if more functional

* more hack

* tools

* functional if not pretty

* Add processing

* working tool calling

* making progress

* keepin on

* Clean config

* working e2e

* update model version

* Remove no longer used stuff

* decouple search results for references and whats shown to model

* fix scripts build errs

* fix broken tests

* update default ref links

* fix broken tests

* input guardrail refactor

* guardrail works well

* simpler validity metric

* add guardrail to server

* add next step todo

* llm refusal msg

* remove TODO comment

* merge fix

* fix unnec changes

* NL feedback

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* fix type in text

* (EAI-991 & EAI-1050): Evaluate and clean up retrieval as a tool (#757)

* refactor GenerateRespose

* Clean up imports

* consolidate generate user prompt to the legacy file

* update test config imports

* Fix broken tests

* get started

* nominally working generate res w/ search

* small refactors

* aint pretty but fully functional

* hacky if more functional

* more hack

* tools

* functional if not pretty

* Add processing

* working tool calling

* making progress

* keepin on

* Clean config

* working e2e

* update model version

* Remove no longer used stuff

* decouple search results for references and whats shown to model

* fix scripts build errs

* fix broken tests

* update default ref links

* fix broken tests

* input guardrail refactor

* guardrail works well

* simpler validity metric

* add guardrail to server

* add next step todo

* llm refusal msg

* remove TODO comment

* evals on new architecture

* Get urls in a way that supports verified answers

* dont eval on retrieved elems if no context

* Cleaner handling

* update trace handling

* update trace handling

* undo git funk

* handle undefined case

* Fix tracing test

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>

* remove console logs + redunancies

---------

Co-authored-by: Ben Perlmutter <mongodben@mongodb.com>
Co-authored-by: Nick Larew <nick.larew@mongodb.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants