chore: improve prompts for better accuracy

Author: kmruiz

src/tools/mongodb/read/aggregate.ts

@@ -35,7 +35,7 @@ const VectorSearchStage = z.object({
             queryVector: z
                 .union([z.string(), z.array(z.number())])
                 .describe(
-                    "The content to search for. The embeddingParameters field is mandatory if the queryVector is a string."
+                    "The content to search for. The embeddingParameters field is mandatory if the queryVector is a string, in that case, the tool generates the embedding automatically using the provided configuration."
                 ),
             numCandidates: z
                 .number()

tests/accuracy/aggregate.test.ts

@@ -27,6 +27,69 @@ describeAccuracyTests([
     },
     {
         prompt: "Run a vectorSearch query on musicfy.songs on path 'title_embeddings' using the index 'titles' with the model voyage-3-large to find all 'hammer of justice' songs.",
+        expectedToolCalls: [
+            {
+                toolName: "collection-indexes",
+                parameters: {
+                    database: "musicfy",
+                    collection: "songs",
+                },
+                optional: true,
+            },
+            {
+                toolName: "aggregate",
+                parameters: {
+                    database: "musicfy",
+                    collection: "songs",
+                    pipeline: [
+                        {
+                            $vectorSearch: {
+                                exact: Matcher.anyOf(Matcher.undefined, Matcher.boolean(false)),
+                                index: "titles",
+                                path: "title_embeddings",
+                                queryVector: "hammer of justice",
+                                embeddingParameters: {
+                                    model: "voyage-3-large",
+                                    outputDimension: Matcher.anyOf(
+                                        Matcher.undefined,
+                                        Matcher.number((n) => n === 1024)
+                                    ),
+                                },
+                                filter: Matcher.emptyObjectOrUndefined,
+                            },
+                        },
+                    ],
+                    responseBytesLimit: Matcher.anyOf(Matcher.number(), Matcher.undefined),
+                },
+            },
+        ],
+        mockedTools: {
+            "collection-indexes": (): CallToolResult => {
+                return {
+                    content: [
+                        {
+                            type: "text",
+                            text: JSON.stringify({
+                                name: "titles",
+                                type: "vectorSearch",
+                                status: "READY",
+                                queryable: true,
+                                latestDefinition: {
+                                    type: "vector",
+                                    path: "title_embeddings",
+                                    numDimensions: 1024,
+                                    quantization: "none",
+                                    similarity: "euclidean",
+                                },
+                            }),
+                        },
+                    ],
+                };
+            },
+        },
+    },
+    {
+        prompt: "Run an exact vectorSearch query on musicfy.songs on path 'title_embeddings' using the index 'titles' with the model voyage-3-large to find 10 'hammer of justice' songs in any order.",
         expectedToolCalls: [
             {
                 toolName: "collection-indexes",
@@ -48,9 +111,15 @@ describeAccuracyTests([
                                 index: "titles",
                                 path: "title_embeddings",
                                 queryVector: "hammer of justice",
+                                limit: 10,
                                 embeddingParameters: {
                                     model: "voyage-3-large",
+                                    outputDimension: Matcher.anyOf(
+                                        Matcher.undefined,
+                                        Matcher.number((n) => n === 1024)
+                                    ),
                                 },
+                                filter: Matcher.emptyObjectOrUndefined,
                             },
                         },
                     ],
@@ -84,7 +153,7 @@ describeAccuracyTests([
         },
     },
     {
-        prompt: "Run a vectorSearch query on mflix.movies on path 'plot_embeddings' with the model voyage-3-large to find all 'sci-fy' movies.",
+        prompt: "Run an approximate vectorSearch query on mflix.movies on path 'plot_embeddings' with the model voyage-3-large to find all 'sci-fy' movies.",
         expectedToolCalls: [
             {
                 toolName: "collection-indexes",
@@ -101,13 +170,18 @@ describeAccuracyTests([
                     pipeline: [
                         {
                             $vectorSearch: {
-                                exact: Matcher.anyOf(Matcher.undefined, Matcher.boolean(true)),
+                                exact: Matcher.anyOf(Matcher.undefined, Matcher.boolean(false)),
                                 index: "my-index",
                                 path: "plot_embeddings",
                                 queryVector: "sci-fy",
                                 embeddingParameters: {
                                     model: "voyage-3-large",
+                                    outputDimension: Matcher.anyOf(
+                                        Matcher.undefined,
+                                        Matcher.number((n) => n === 1024)
+                                    ),
                                 },
+                                filter: Matcher.emptyObjectOrUndefined,
                             },
                         },
                     ],