Skip to content

(EAI-1190) fix eval experiments #845

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.

Sign up for GitHub

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 6 commits into from
Aug 4, 2025
Merged

(EAI-1190) fix eval experiments #845

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d3d74e1
makeGenerateResponse args made optional, skillsWuestionsTest eval fixed
yakubova92 Jul 24, 2025
b083370
fix all eval experiments
yakubova92 Jul 24, 2025
875aa27
build includes evals dir
yakubova92 Jul 24, 2025
299ce76
Merge branch 'main' into EAI-1190
yakubova92 Aug 4, 2025
006512b
fix build errors
yakubova92 Aug 4, 2025
95bdb98
using prebuild script to check for errors in complete package
yakubova92 Aug 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions packages/chatbot-server-mongodb-public/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@
".": "./build/lib.js"
},
"scripts": {
"build:check": "tsc --noEmit --project tsconfig.json",
"prebuild": "npm run build:check",
"build": "rm -rf ./build/ && tsc -b tsconfig.build.json",
"dev": "nodemon src/index.ts",
"format": "prettier ./src --write",
Expand Down
2 changes: 1 addition & 1 deletion packages/chatbot-server-mongodb-public/src/eval/bin/generateEvalCasesYamlFromCSV.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ async function main({
);
const urlsNotIngested = await pageStore.getMissingPagesByUrl({
expectedUrls,
urlTransformer: normalizeUrl,
urlTransformer: (url) => normalizeUrl({ url }),
});
if (urlsNotIngested.length > 0) {
console.warn(
Expand Down
1 change: 0 additions & 1 deletion packages/chatbot-server-mongodb-public/src/eval/experiments/allScorersTest.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@ import fs from "fs";
import path from "path";
import { makeConversationEval } from "../ConversationEval";
import { makeGenerateResponse } from "../../config";
import { addMessageToConversationStream } from "../../processors/generateResponseWithSearchTool";

async function conversationEval() {
// Get all the conversation eval cases from YAML
Expand Down
1 change: 0 additions & 1 deletion packages/chatbot-server-mongodb-public/src/eval/experiments/architectureCenter.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@ import fs from "fs";
import path from "path";
import { makeConversationEval } from "../ConversationEval";
import { makeGenerateResponse } from "../../config";
import { addMessageToConversationStream } from "../../processors/generateResponseWithSearchTool";

async function conversationEval() {
// Get ONLY architecture center conversations
Expand Down
1 change: 0 additions & 1 deletion packages/chatbot-server-mongodb-public/src/eval/experiments/customSystemPrompt.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@ import {
} from "../evalHelpers";
import { makeConversationEval } from "../ConversationEval";
import { closeDbConnections, makeGenerateResponse } from "../../config";
import { responsesApiStream } from "../../processors/generateResponseWithSearchTool";

const conversationEvalCases: ConversationEvalCase[] = [
// Test 1: Basic custom system prompt override
Expand Down
1 change: 0 additions & 1 deletion packages/chatbot-server-mongodb-public/src/eval/experiments/dotcomQuestionsTest.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@ import fs from "fs";
import path from "path";
import { makeConversationEval } from "../ConversationEval";
import { makeGenerateResponse } from "../../config";
import { addMessageToConversationStream } from "../../processors/generateResponseWithSearchTool";

async function conversationEval() {
// Get dotcom question set eval cases from YAML
Expand Down
7 changes: 5 additions & 2 deletions packages/chatbot-server-mongodb-public/src/tools/search.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ import "dotenv/config";
import {
Eval,
EvalCase,
EvalParameters,
EvalScorer,
EvalTask,
} from "mongodb-rag-core/braintrust";
Expand Down Expand Up @@ -62,8 +63,10 @@ const { k } = retrievalConfig.findNearestNeighborsOptions;
const retrieveRelevantContentEvalTask: EvalTask<
RetrievalEvalCaseInput,
RetrievalTaskOutput,
RetrievalEvalCaseExpected
> = async function (data) {
RetrievalEvalCaseExpected,
void,
EvalParameters
> = async function (data: RetrievalEvalCaseInput) {
// TODO: (EAI-991) implement retrieval task for evaluation
const extractedMetadata: MongoDbSearchToolArgs = {
productName: null,
Expand Down
1 change: 1 addition & 0 deletions packages/mongodb-rag-core/src/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,3 +24,4 @@ export * from "./VectorStore";
export * from "./arrayFilters";
export * from "./assertEnvVars";
export * from "./getEnv";
export * from "./mongoDbMetadata";