LocalAI/pkg/functions/grammar_json_schema_test.go
Ettore Di Giacinto efa32a2677
feat(grammar): support models with specific construct (#2291)
When enabling grammar with functions, it might be useful to
allow more flexibility to support models that are fine-tuned against returning
function calls of the form of { "name": "function_name", "arguments" {...} }
rather then { "function": "function_name", "arguments": {..} }.

This might call out to a more generic approach later on, but for the moment being we can easily support both
as we have just to specific different types.

If needed we can expand on this later on

Signed-off-by: mudler <mudler@localai.io>
2024-05-12 01:13:22 +02:00

300 lines
8.7 KiB
Go

package functions_test
import (
"strings"
. "github.com/go-skynet/LocalAI/pkg/functions"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
)
const (
testInput1 = `
{
"oneOf": [
{
"type": "object",
"properties": {
"function": {"const": "create_event"},
"arguments": {
"type": "object",
"properties": {
"title": {"type": "string"},
"date": {"type": "string"},
"time": {"type": "string"}
}
}
}
},
{
"type": "object",
"properties": {
"function": {"const": "search"},
"arguments": {
"type": "object",
"properties": {
"query": {"type": "string"}
}
}
}
}
]
}`
inputResult1 = `root-0-function ::= "\"create_event\""
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"function\"" space ":" space root-0-function "}" space
root-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
root ::= root-0 | root-1
space ::= " "?
root-0-arguments ::= "{" space "\"date\"" space ":" space string "," space "\"time\"" space ":" space string "," space "\"title\"" space ":" space string "}" space
root-1 ::= "{" space "\"arguments\"" space ":" space root-1-arguments "," space "\"function\"" space ":" space root-1-function "}" space
string ::= "\"" (
[^"\\] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* "\"" space
root-1-function ::= "\"search\""`
inputResult2 = `root-0-function ::= "\"create_event\""
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"function\"" space ":" space root-0-function "}" space
root-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
realvalue ::= root-0 | root-1
root ::= arr | realvalue
space ::= " "?
root-0-arguments ::= "{" space "\"date\"" space ":" space string "," space "\"time\"" space ":" space string "," space "\"title\"" space ":" space string "}" space
root-1 ::= "{" space "\"arguments\"" space ":" space root-1-arguments "," space "\"function\"" space ":" space root-1-function "}" space
string ::= "\"" (
[^"\\] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* "\"" space
arr ::=
"[\n" (
realvalue
(",\n" realvalue)*
)? "]"
root-1-function ::= "\"search\""`
testInput2 = `
{
"oneOf": [
{
"type": "object",
"properties": {
"name": {"const": "create_event"},
"arguments": {
"type": "object",
"properties": {
"title": {"type": "string"},
"date": {"type": "string"},
"time": {"type": "string"}
}
}
}
},
{
"type": "object",
"properties": {
"name": {"const": "search"},
"arguments": {
"type": "object",
"properties": {
"query": {"type": "string"}
}
}
}
}
]
}`
inputResult3 = `root-0-name ::= "\"create_event\""
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"name\"" space ":" space root-0-name "}" space
root-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
root ::= root-0 | root-1
space ::= " "?
root-0-arguments ::= "{" space "\"date\"" space ":" space string "," space "\"time\"" space ":" space string "," space "\"title\"" space ":" space string "}" space
root-1 ::= "{" space "\"arguments\"" space ":" space root-1-arguments "," space "\"name\"" space ":" space root-1-name "}" space
string ::= "\"" (
[^"\\] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* "\"" space
root-1-name ::= "\"search\""`
inputResult4 = `root-0-name ::= "\"create_event\""
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"name\"" space ":" space root-0-name "}" space
root-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
realvalue ::= root-0 | root-1
root ::= arr | realvalue
space ::= " "?
root-0-arguments ::= "{" space "\"date\"" space ":" space string "," space "\"time\"" space ":" space string "," space "\"title\"" space ":" space string "}" space
root-1 ::= "{" space "\"arguments\"" space ":" space root-1-arguments "," space "\"name\"" space ":" space root-1-name "}" space
string ::= "\"" (
[^"\\] |
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
)* "\"" space
arr ::=
"[\n" (
realvalue
(",\n" realvalue)*
)? "]"
root-1-name ::= "\"search\""`
)
var _ = Describe("JSON schema grammar tests", func() {
Context("JSON", func() {
It("generates a valid grammar from JSON schema", func() {
grammar := NewJSONSchemaConverter("").GrammarFromBytes([]byte(testInput1), false)
results := strings.Split(inputResult1, "\n")
for _, r := range results {
if r != "" {
Expect(grammar).To(ContainSubstring(r))
}
}
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))))
})
It("generates a valid grammar from JSON schema", func() {
grammar := NewJSONSchemaConverter("").GrammarFromBytes([]byte(testInput2), false)
results := strings.Split(inputResult3, "\n")
for _, r := range results {
if r != "" {
Expect(grammar).To(ContainSubstring(r))
}
}
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))))
})
It("generates a valid grammar from JSON Objects", func() {
structuredGrammar := JSONFunctionStructureFunction{
OneOf: []ItemFunction{
{
Type: "object",
Properties: FunctionProperties{
Function: FunctionName{
Const: "create_event",
},
Arguments: Argument{ // this is OpenAI's parameter
Type: "object",
Properties: map[string]interface{}{
"title": map[string]string{"type": "string"},
"date": map[string]string{"type": "string"},
"time": map[string]string{"type": "string"},
},
},
},
},
{
Type: "object",
Properties: FunctionProperties{
Function: FunctionName{
Const: "search",
},
Arguments: Argument{
Type: "object",
Properties: map[string]interface{}{
"query": map[string]string{"type": "string"},
},
},
},
},
}}
grammar := structuredGrammar.Grammar("", false)
results := strings.Split(inputResult1, "\n")
for _, r := range results {
if r != "" {
Expect(grammar).To(ContainSubstring(r))
}
}
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))))
})
It("generates a valid grammar from JSON Objects for multiple function return", func() {
structuredGrammar := JSONFunctionStructureFunction{
OneOf: []ItemFunction{
{
Type: "object",
Properties: FunctionProperties{
Function: FunctionName{
Const: "create_event",
},
Arguments: Argument{ // this is OpenAI's parameter
Type: "object",
Properties: map[string]interface{}{
"title": map[string]string{"type": "string"},
"date": map[string]string{"type": "string"},
"time": map[string]string{"type": "string"},
},
},
},
},
{
Type: "object",
Properties: FunctionProperties{
Function: FunctionName{
Const: "search",
},
Arguments: Argument{
Type: "object",
Properties: map[string]interface{}{
"query": map[string]string{"type": "string"},
},
},
},
},
}}
grammar := structuredGrammar.Grammar("", true)
results := strings.Split(inputResult2, "\n")
for _, r := range results {
if r != "" {
Expect(grammar).To(ContainSubstring(r))
}
}
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))), grammar)
})
It("generates a valid grammar from JSON Objects for multiple function return", func() {
structuredGrammar := JSONFunctionStructureName{
OneOf: []ItemName{
{
Type: "object",
Properties: NameProperties{
Function: FunctionName{
Const: "create_event",
},
Arguments: Argument{ // this is OpenAI's parameter
Type: "object",
Properties: map[string]interface{}{
"title": map[string]string{"type": "string"},
"date": map[string]string{"type": "string"},
"time": map[string]string{"type": "string"},
},
},
},
},
{
Type: "object",
Properties: NameProperties{
Function: FunctionName{
Const: "search",
},
Arguments: Argument{
Type: "object",
Properties: map[string]interface{}{
"query": map[string]string{"type": "string"},
},
},
},
},
}}
grammar := structuredGrammar.Grammar("", true)
results := strings.Split(inputResult4, "\n")
for _, r := range results {
if r != "" {
Expect(grammar).To(ContainSubstring(r))
}
}
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))), grammar)
})
})
})