From db980de4926c5561c0ab60aa64fbe7cde98e2896 Mon Sep 17 00:00:00 2001
From: sunilmujumdar <55596447+sunilmujumdar@users.noreply.github.com>
Date: Thu, 9 Nov 2023 19:47:38 -0800
Subject: [PATCH] Fix(Indexing): Improve error reporting for missing data
 during vector searches (#60)

Description: If the vector parameter in a similar_to function call is a
variable that evaluates to NULL then we report it as a parsing (syntax)
error.

The fix, instead of reporting a parsing error,  returns an empty result.

Closes: HYP-302

---------

Co-authored-by: Bill Province <billprovince@gmail.com>
---
 ...ing-directive-with-similar-queries.graphql |  21 +
 ...ing-directive-with-similar-queries.graphql | 584 ++++++++++++++++++
 2 files changed, 605 insertions(+)
 create mode 100644 graphql/schema/testdata/schemagen/input/embedding-directive-with-similar-queries.graphql
 create mode 100644 graphql/schema/testdata/schemagen/output/embedding-directive-with-similar-queries.graphql

diff --git a/graphql/schema/testdata/schemagen/input/embedding-directive-with-similar-queries.graphql b/graphql/schema/testdata/schemagen/input/embedding-directive-with-similar-queries.graphql
new file mode 100644
index 00000000000..8a267fe6dd7
--- /dev/null
+++ b/graphql/schema/testdata/schemagen/input/embedding-directive-with-similar-queries.graphql
@@ -0,0 +1,21 @@
+# simple user product GraphQL API - v0.4
+
+type Product {
+  id: String! @id
+  description: String
+  title: String
+  imageUrl: String
+  product_vector: [Float] @hm_embedding 
+}
+
+type Purchase @lambdaOnMutate(add: true){
+  user: User @hasInverse(field: "purchase_history")
+  product: Product
+  date: DateTime @search(by: [day])
+}
+
+type User  {
+  email: String!  @id
+  purchase_history: [Purchase] 
+  user_vector: [Float] @hm_embedding 
+}
diff --git a/graphql/schema/testdata/schemagen/output/embedding-directive-with-similar-queries.graphql b/graphql/schema/testdata/schemagen/output/embedding-directive-with-similar-queries.graphql
new file mode 100644
index 00000000000..9b4faff34a0
--- /dev/null
+++ b/graphql/schema/testdata/schemagen/output/embedding-directive-with-similar-queries.graphql
@@ -0,0 +1,584 @@
+#######################
+# Input Schema
+#######################
+
+type Product {
+	id: String! @id
+	description: String
+	title: String
+	imageUrl: String
+	product_vector: [Float] @hm_embedding
+}
+
+type Purchase @lambdaOnMutate(add: true) {
+	user(filter: UserFilter): User @hasInverse(field: "purchase_history")
+	product(filter: ProductFilter): Product
+	date: DateTime @search(by: [day])
+}
+
+type User {
+	email: String! @id
+	purchase_history(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase] @hasInverse(field: user)
+	user_vector: [Float] @hm_embedding
+	purchase_historyAggregate(filter: PurchaseFilter): PurchaseAggregateResult
+}
+
+#######################
+# Extended Definitions
+#######################
+
+"""
+The Int64 scalar type represents a signed 64‐bit numeric non‐fractional value.
+Int64 can represent values in range [-(2^63),(2^63 - 1)].
+"""
+scalar Int64
+
+"""
+The DateTime scalar type represents date and time as a string in RFC3339 format.
+For example: "1985-04-12T23:20:50.52Z" represents 20 mins 50.52 secs after the 23rd hour of Apr 12th 1985 in UTC.
+"""
+scalar DateTime
+
+input IntRange{
+	min: Int!
+	max: Int!
+}
+
+input FloatRange{
+	min: Float!
+	max: Float!
+}
+
+input Int64Range{
+	min: Int64!
+	max: Int64!
+}
+
+input DateTimeRange{
+	min: DateTime!
+	max: DateTime!
+}
+
+input StringRange{
+	min: String!
+	max: String!
+}
+
+enum DgraphIndex {
+	int
+	int64
+	float
+	bool
+	hash
+	exact
+	term
+	fulltext
+	trigram
+	regexp
+	year
+	month
+	day
+	hour
+	geo
+}
+
+input AuthRule {
+	and: [AuthRule]
+	or: [AuthRule]
+	not: AuthRule
+	rule: String
+}
+
+enum HTTPMethod {
+	GET
+	POST
+	PUT
+	PATCH
+	DELETE
+}
+
+enum Mode {
+	BATCH
+	SINGLE
+}
+
+input CustomHTTP {
+	url: String!
+	method: HTTPMethod!
+	body: String
+	graphql: String
+	mode: Mode
+	forwardHeaders: [String!]
+	secretHeaders: [String!]
+	introspectionHeaders: [String!]
+	skipIntrospection: Boolean
+}
+
+type Point {
+	longitude: Float!
+	latitude: Float!
+}
+
+input PointRef {
+	longitude: Float!
+	latitude: Float!
+}
+
+input NearFilter {
+	distance: Float!
+	coordinate: PointRef!
+}
+
+input PointGeoFilter {
+	near: NearFilter
+	within: WithinFilter
+}
+
+type PointList {
+	points: [Point!]!
+}
+
+input PointListRef {
+	points: [PointRef!]!
+}
+
+type Polygon {
+	coordinates: [PointList!]!
+}
+
+input PolygonRef {
+	coordinates: [PointListRef!]!
+}
+
+type MultiPolygon {
+	polygons: [Polygon!]!
+}
+
+input MultiPolygonRef {
+	polygons: [PolygonRef!]!
+}
+
+input WithinFilter {
+	polygon: PolygonRef!
+}
+
+input ContainsFilter {
+	point: PointRef
+	polygon: PolygonRef
+}
+
+input IntersectsFilter {
+	polygon: PolygonRef
+	multiPolygon: MultiPolygonRef
+}
+
+input PolygonGeoFilter {
+	near: NearFilter
+	within: WithinFilter
+	contains: ContainsFilter
+	intersects: IntersectsFilter
+}
+
+input GenerateQueryParams {
+	get: Boolean
+	query: Boolean
+	password: Boolean
+	aggregate: Boolean
+}
+
+input GenerateMutationParams {
+	add: Boolean
+	update: Boolean
+	delete: Boolean
+}
+
+directive @hasInverse(field: String!) on FIELD_DEFINITION
+directive @search(by: [DgraphIndex!]) on FIELD_DEFINITION
+directive @hm_embedding on FIELD_DEFINITION
+directive @dgraph(type: String, pred: String) on OBJECT | INTERFACE | FIELD_DEFINITION
+directive @id(interface: Boolean) on FIELD_DEFINITION
+directive @withSubscription on OBJECT | INTERFACE | FIELD_DEFINITION
+directive @secret(field: String!, pred: String) on OBJECT | INTERFACE
+directive @auth(
+	password: AuthRule
+	query: AuthRule,
+	add: AuthRule,
+	update: AuthRule,
+	delete: AuthRule) on OBJECT | INTERFACE
+directive @custom(http: CustomHTTP, dql: String) on FIELD_DEFINITION
+directive @remote on OBJECT | INTERFACE | UNION | INPUT_OBJECT | ENUM
+directive @remoteResponse(name: String) on FIELD_DEFINITION
+directive @cascade(fields: [String]) on FIELD
+directive @lambda on FIELD_DEFINITION
+directive @lambdaOnMutate(add: Boolean, update: Boolean, delete: Boolean) on OBJECT | INTERFACE
+directive @cacheControl(maxAge: Int!) on QUERY
+directive @generate(
+	query: GenerateQueryParams,
+	mutation: GenerateMutationParams,
+	subscription: Boolean) on OBJECT | INTERFACE
+
+input IntFilter {
+	eq: Int
+	in: [Int]
+	le: Int
+	lt: Int
+	ge: Int
+	gt: Int
+	between: IntRange
+}
+
+input Int64Filter {
+	eq: Int64
+	in: [Int64]
+	le: Int64
+	lt: Int64
+	ge: Int64
+	gt: Int64
+	between: Int64Range
+}
+
+input FloatFilter {
+	eq: Float
+	in: [Float]
+	le: Float
+	lt: Float
+	ge: Float
+	gt: Float
+	between: FloatRange
+}
+
+input DateTimeFilter {
+	eq: DateTime
+	in: [DateTime]
+	le: DateTime
+	lt: DateTime
+	ge: DateTime
+	gt: DateTime
+	between: DateTimeRange
+}
+
+input StringTermFilter {
+	allofterms: String
+	anyofterms: String
+}
+
+input StringRegExpFilter {
+	regexp: String
+}
+
+input StringFullTextFilter {
+	alloftext: String
+	anyoftext: String
+}
+
+input StringExactFilter {
+	eq: String
+	in: [String]
+	le: String
+	lt: String
+	ge: String
+	gt: String
+	between: StringRange
+}
+
+input StringHashFilter {
+	eq: String
+	in: [String]
+}
+
+#######################
+# Generated Types
+#######################
+
+type AddProductPayload {
+	product(filter: ProductFilter, order: ProductOrder, first: Int, offset: Int): [Product]
+	numUids: Int
+}
+
+type AddPurchasePayload {
+	purchase(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase]
+	numUids: Int
+}
+
+type AddUserPayload {
+	user(filter: UserFilter, order: UserOrder, first: Int, offset: Int): [User]
+	numUids: Int
+}
+
+type DeleteProductPayload {
+	product(filter: ProductFilter, order: ProductOrder, first: Int, offset: Int): [Product]
+	msg: String
+	numUids: Int
+}
+
+type DeletePurchasePayload {
+	purchase(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase]
+	msg: String
+	numUids: Int
+}
+
+type DeleteUserPayload {
+	user(filter: UserFilter, order: UserOrder, first: Int, offset: Int): [User]
+	msg: String
+	numUids: Int
+}
+
+type ProductAggregateResult {
+	count: Int
+	idMin: String
+	idMax: String
+	descriptionMin: String
+	descriptionMax: String
+	titleMin: String
+	titleMax: String
+	imageUrlMin: String
+	imageUrlMax: String
+}
+
+type ProductWithDistance @dgraph(type: "Product") {
+	id: String! @id
+	description: String
+	title: String
+	imageUrl: String
+	product_vector: [Float] @hm_embedding
+	hm_distance: Float
+}
+
+type PurchaseAggregateResult {
+	count: Int
+	dateMin: DateTime
+	dateMax: DateTime
+}
+
+type UpdateProductPayload {
+	product(filter: ProductFilter, order: ProductOrder, first: Int, offset: Int): [Product]
+	numUids: Int
+}
+
+type UpdatePurchasePayload {
+	purchase(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase]
+	numUids: Int
+}
+
+type UpdateUserPayload {
+	user(filter: UserFilter, order: UserOrder, first: Int, offset: Int): [User]
+	numUids: Int
+}
+
+type UserAggregateResult {
+	count: Int
+	emailMin: String
+	emailMax: String
+}
+
+type UserWithDistance @dgraph(type: "User") {
+	email: String! @id
+	purchase_history(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase] @hasInverse(field: user)
+	user_vector: [Float] @hm_embedding
+	purchase_historyAggregate(filter: PurchaseFilter): PurchaseAggregateResult
+}
+
+#######################
+# Generated Enums
+#######################
+
+enum ProductEmbedding {
+	product_vector
+}
+
+enum ProductHasFilter {
+	id
+	description
+	title
+	imageUrl
+	product_vector
+}
+
+enum ProductOrderable {
+	id
+	description
+	title
+	imageUrl
+}
+
+enum PurchaseHasFilter {
+	user
+	product
+	date
+}
+
+enum PurchaseOrderable {
+	date
+}
+
+enum UserEmbedding {
+	user_vector
+}
+
+enum UserHasFilter {
+	email
+	purchase_history
+	user_vector
+}
+
+enum UserOrderable {
+	email
+}
+
+#######################
+# Generated Inputs
+#######################
+
+input AddProductInput {
+	id: String!
+	description: String
+	title: String
+	imageUrl: String
+	product_vector: [Float]
+}
+
+input AddPurchaseInput {
+	user: UserRef
+	product: ProductRef
+	date: DateTime
+}
+
+input AddUserInput {
+	email: String!
+	purchase_history: [PurchaseRef]
+	user_vector: [Float]
+}
+
+input ProductFilter {
+	id: StringHashFilter
+	has: [ProductHasFilter]
+	and: [ProductFilter]
+	or: [ProductFilter]
+	not: ProductFilter
+}
+
+input ProductOrder {
+	asc: ProductOrderable
+	desc: ProductOrderable
+	then: ProductOrder
+}
+
+input ProductPatch {
+	description: String
+	title: String
+	imageUrl: String
+	product_vector: [Float]
+}
+
+input ProductRef {
+	id: String
+	description: String
+	title: String
+	imageUrl: String
+	product_vector: [Float]
+}
+
+input PurchaseFilter {
+	date: DateTimeFilter
+	has: [PurchaseHasFilter]
+	and: [PurchaseFilter]
+	or: [PurchaseFilter]
+	not: PurchaseFilter
+}
+
+input PurchaseOrder {
+	asc: PurchaseOrderable
+	desc: PurchaseOrderable
+	then: PurchaseOrder
+}
+
+input PurchasePatch {
+	user: UserRef
+	product: ProductRef
+	date: DateTime
+}
+
+input PurchaseRef {
+	user: UserRef
+	product: ProductRef
+	date: DateTime
+}
+
+input UpdateProductInput {
+	filter: ProductFilter!
+	set: ProductPatch
+	remove: ProductPatch
+}
+
+input UpdatePurchaseInput {
+	filter: PurchaseFilter!
+	set: PurchasePatch
+	remove: PurchasePatch
+}
+
+input UpdateUserInput {
+	filter: UserFilter!
+	set: UserPatch
+	remove: UserPatch
+}
+
+input UserFilter {
+	email: StringHashFilter
+	has: [UserHasFilter]
+	and: [UserFilter]
+	or: [UserFilter]
+	not: UserFilter
+}
+
+input UserOrder {
+	asc: UserOrderable
+	desc: UserOrderable
+	then: UserOrder
+}
+
+input UserPatch {
+	purchase_history: [PurchaseRef]
+	user_vector: [Float]
+}
+
+input UserRef {
+	email: String
+	purchase_history: [PurchaseRef]
+	user_vector: [Float]
+}
+
+#######################
+# Generated Query
+#######################
+
+type Query {
+	getProduct(id: String!): Product
+	querySimilarProductById(id: String!, by: ProductEmbedding, topK: Int!): [ProductWithDistance]
+	querySimilarProductByEmbedding(by: ProductEmbedding, topK: Int!, vector: [Float!]): [ProductWithDistance]
+	queryProduct(filter: ProductFilter, order: ProductOrder, first: Int, offset: Int): [Product]
+	aggregateProduct(filter: ProductFilter): ProductAggregateResult
+	queryPurchase(filter: PurchaseFilter, order: PurchaseOrder, first: Int, offset: Int): [Purchase]
+	aggregatePurchase(filter: PurchaseFilter): PurchaseAggregateResult
+	getUser(email: String!): User
+	querySimilarUserById(email: String!, by: UserEmbedding, topK: Int!): [UserWithDistance]
+	querySimilarUserByEmbedding(by: UserEmbedding, topK: Int!, vector: [Float!]): [UserWithDistance]
+	queryUser(filter: UserFilter, order: UserOrder, first: Int, offset: Int): [User]
+	aggregateUser(filter: UserFilter): UserAggregateResult
+}
+
+#######################
+# Generated Mutations
+#######################
+
+type Mutation {
+	addProduct(input: [AddProductInput!]!, upsert: Boolean): AddProductPayload
+	updateProduct(input: UpdateProductInput!): UpdateProductPayload
+	deleteProduct(filter: ProductFilter!): DeleteProductPayload
+	addPurchase(input: [AddPurchaseInput!]!): AddPurchasePayload
+	updatePurchase(input: UpdatePurchaseInput!): UpdatePurchasePayload
+	deletePurchase(filter: PurchaseFilter!): DeletePurchasePayload
+	addUser(input: [AddUserInput!]!, upsert: Boolean): AddUserPayload
+	updateUser(input: UpdateUserInput!): UpdateUserPayload
+	deleteUser(filter: UserFilter!): DeleteUserPayload
+}
+