mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 18:45:00 +00:00
feat(functions): mixed JSON BNF grammars (#2328)
feat(functions): support mixed JSON BNF grammar This PR provides new options to control how functions are extracted from the LLM, and also provides more control on how JSON grammars can be used (also in conjunction). New YAML settings introduced: - `grammar_message`: when enabled, the generated grammar can also decide to push strings and not only JSON objects. This allows the LLM to pick to either respond freely or using JSON. - `grammar_prefix`: Allows to prefix a string to the JSON grammar definition. - `replace_results`: Is a map that allows to replace strings in the LLM result. As an example, consider the following settings for Hermes-2-Pro-Mistral, which allow extracting both JSON results coming from the model, and the ones coming from the grammar: ```yaml function: # disable injecting the "answer" tool disable_no_action: true # This allows the grammar to also return messages grammar_message: true # Suffix to add to the grammar grammar_prefix: '<tool_call>\n' return_name_in_function_response: true # Without grammar uncomment the lines below # Warning: this is relying only on the capability of the # LLM model to generate the correct function call. # no_grammar: true # json_regex_match: "(?s)<tool_call>(.*?)</tool_call>" replace_results: "<tool_call>": "" "\'": "\"" ``` Note: To disable entirely grammars usage in the example above, uncomment the `no_grammar` and `json_regex_match`. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
c89271b2e4
commit
beb598e4f9
4 changed files with 283 additions and 126 deletions
|
@ -219,15 +219,15 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, startup
|
||||||
// Handle if we should return "name" instead of "functions"
|
// Handle if we should return "name" instead of "functions"
|
||||||
if config.FunctionsConfig.FunctionName {
|
if config.FunctionsConfig.FunctionName {
|
||||||
jsStruct := funcs.ToJSONNameStructure()
|
jsStruct := funcs.ToJSONNameStructure()
|
||||||
config.Grammar = jsStruct.Grammar("", config.FunctionsConfig.ParallelCalls)
|
config.Grammar = jsStruct.Grammar(config.FunctionsConfig.GrammarPrefix, "", config.FunctionsConfig.ParallelCalls, config.FunctionsConfig.GrammarMessage)
|
||||||
} else {
|
} else {
|
||||||
jsStruct := funcs.ToJSONFunctionStructure()
|
jsStruct := funcs.ToJSONFunctionStructure()
|
||||||
config.Grammar = jsStruct.Grammar("", config.FunctionsConfig.ParallelCalls)
|
config.Grammar = jsStruct.Grammar(config.FunctionsConfig.GrammarPrefix, "", config.FunctionsConfig.ParallelCalls, config.FunctionsConfig.GrammarMessage)
|
||||||
}
|
}
|
||||||
case input.JSONFunctionGrammarObject != nil:
|
case input.JSONFunctionGrammarObject != nil:
|
||||||
config.Grammar = input.JSONFunctionGrammarObject.Grammar("", config.FunctionsConfig.ParallelCalls)
|
config.Grammar = input.JSONFunctionGrammarObject.Grammar(config.FunctionsConfig.GrammarPrefix, "", config.FunctionsConfig.ParallelCalls, config.FunctionsConfig.GrammarMessage)
|
||||||
case input.JSONFunctionGrammarObjectName != nil:
|
case input.JSONFunctionGrammarObjectName != nil:
|
||||||
config.Grammar = input.JSONFunctionGrammarObjectName.Grammar("", config.FunctionsConfig.ParallelCalls)
|
config.Grammar = input.JSONFunctionGrammarObjectName.Grammar(config.FunctionsConfig.GrammarPrefix, "", config.FunctionsConfig.ParallelCalls, config.FunctionsConfig.GrammarMessage)
|
||||||
default:
|
default:
|
||||||
// Force picking one of the functions by the request
|
// Force picking one of the functions by the request
|
||||||
if config.FunctionToCall() != "" {
|
if config.FunctionToCall() != "" {
|
||||||
|
|
|
@ -8,6 +8,8 @@ import (
|
||||||
"regexp"
|
"regexp"
|
||||||
"sort"
|
"sort"
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
|
"github.com/go-skynet/LocalAI/pkg/utils"
|
||||||
)
|
)
|
||||||
|
|
||||||
const (
|
const (
|
||||||
|
@ -48,6 +50,10 @@ var (
|
||||||
[^"\\] |
|
[^"\\] |
|
||||||
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
)* "\"" space`,
|
)* "\"" space`,
|
||||||
|
"freestring": `(
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space`,
|
||||||
"null": `"null" space`,
|
"null": `"null" space`,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -111,22 +117,54 @@ const array = `arr ::=
|
||||||
(",\n" realvalue)*
|
(",\n" realvalue)*
|
||||||
)? "]"`
|
)? "]"`
|
||||||
|
|
||||||
func (sc *JSONSchemaConverter) finalizeGrammar(maybeArray bool) string {
|
func (sc *JSONSchemaConverter) finalizeGrammar(suffix string, maybeArray, maybeString bool) string {
|
||||||
var lines []string
|
var lines []string
|
||||||
|
|
||||||
|
swapRoot := maybeArray || maybeString || suffix != ""
|
||||||
|
|
||||||
// write down the computed rules.
|
// write down the computed rules.
|
||||||
// if maybeArray is true, we need to add the array rule and slightly tweak the root rule
|
// if maybeArray is true, we need to add the array rule and slightly tweak the root rule
|
||||||
for name, rule := range sc.rules {
|
for name, rule := range sc.rules {
|
||||||
if maybeArray && name == "root" {
|
if swapRoot && name == "root" {
|
||||||
name = "realvalue"
|
name = "realvalue"
|
||||||
}
|
}
|
||||||
lines = append(lines, fmt.Sprintf("%s ::= %s", name, rule))
|
lines = append(lines, fmt.Sprintf("%s ::= %s", name, rule))
|
||||||
}
|
}
|
||||||
|
|
||||||
if maybeArray {
|
if !swapRoot {
|
||||||
lines = append(lines, fmt.Sprintf("%s ::= %s", "root", "arr | realvalue"))
|
return strings.Join(lines, "\n")
|
||||||
lines = append(lines, array)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
newRoot := "realvalue"
|
||||||
|
if maybeArray {
|
||||||
|
newRoot = "arr | realvalue"
|
||||||
|
}
|
||||||
|
|
||||||
|
if suffix != "" {
|
||||||
|
// quote newlines in suffix
|
||||||
|
suffix = utils.EscapeNewLines(suffix)
|
||||||
|
|
||||||
|
if maybeArray && maybeString {
|
||||||
|
newRoot = "(" + newRoot + ")"
|
||||||
|
}
|
||||||
|
|
||||||
|
if maybeString {
|
||||||
|
//newRoot = "( (\"" + suffix + "\" " + newRoot + ") | freestring ) "
|
||||||
|
newRoot = "( \"" + suffix + "\" " + newRoot + " | freestring ) "
|
||||||
|
} else {
|
||||||
|
newRoot = "\"" + suffix + "\" " + "" + newRoot + ""
|
||||||
|
}
|
||||||
|
} else if maybeString {
|
||||||
|
if maybeArray {
|
||||||
|
// newRoot = "(" + newRoot + ")"
|
||||||
|
}
|
||||||
|
|
||||||
|
newRoot = "freestring | " + newRoot
|
||||||
|
}
|
||||||
|
|
||||||
|
lines = append(lines, fmt.Sprintf("%s ::= %s", "root", newRoot))
|
||||||
|
lines = append(lines, array)
|
||||||
|
|
||||||
return strings.Join(lines, "\n")
|
return strings.Join(lines, "\n")
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -251,15 +289,16 @@ func (sc *JSONSchemaConverter) resolveReference(ref string, rootSchema map[strin
|
||||||
|
|
||||||
return def
|
return def
|
||||||
}
|
}
|
||||||
func (sc *JSONSchemaConverter) Grammar(schema map[string]interface{}, maybeArray bool) string {
|
func (sc *JSONSchemaConverter) Grammar(suffix string, schema map[string]interface{}, maybeArray, maybeString bool) string {
|
||||||
|
sc.addRule("freestring", PRIMITIVE_RULES["freestring"])
|
||||||
sc.visit(schema, "", schema)
|
sc.visit(schema, "", schema)
|
||||||
return sc.finalizeGrammar(maybeArray)
|
return sc.finalizeGrammar(suffix, maybeArray, maybeString)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (sc *JSONSchemaConverter) GrammarFromBytes(b []byte, maybeArray bool) string {
|
func (sc *JSONSchemaConverter) GrammarFromBytes(suffix string, b []byte, maybeArray, maybeString bool) string {
|
||||||
var schema map[string]interface{}
|
var schema map[string]interface{}
|
||||||
_ = json.Unmarshal(b, &schema)
|
_ = json.Unmarshal(b, &schema)
|
||||||
return sc.Grammar(schema, maybeArray)
|
return sc.Grammar(suffix, schema, maybeArray, maybeString)
|
||||||
}
|
}
|
||||||
|
|
||||||
func jsonString(v interface{}) string {
|
func jsonString(v interface{}) string {
|
||||||
|
@ -302,9 +341,9 @@ type JSONFunctionStructureName struct {
|
||||||
Defs map[string]interface{} `json:"$defs,omitempty"`
|
Defs map[string]interface{} `json:"$defs,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
func (j JSONFunctionStructureName) Grammar(propOrder string, maybeArray bool) string {
|
func (j JSONFunctionStructureName) Grammar(suffix string, propOrder string, maybeArray, maybeString bool) string {
|
||||||
dat, _ := json.Marshal(j)
|
dat, _ := json.Marshal(j)
|
||||||
return NewJSONSchemaConverter(propOrder).GrammarFromBytes(dat, maybeArray)
|
return NewJSONSchemaConverter(propOrder).GrammarFromBytes(suffix, dat, maybeArray, maybeString)
|
||||||
}
|
}
|
||||||
|
|
||||||
type JSONFunctionStructureFunction struct {
|
type JSONFunctionStructureFunction struct {
|
||||||
|
@ -313,7 +352,7 @@ type JSONFunctionStructureFunction struct {
|
||||||
Defs map[string]interface{} `json:"$defs,omitempty"`
|
Defs map[string]interface{} `json:"$defs,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
func (j JSONFunctionStructureFunction) Grammar(propOrder string, maybeArray bool) string {
|
func (j JSONFunctionStructureFunction) Grammar(suffix string, propOrder string, maybeArray, maybeString bool) string {
|
||||||
dat, _ := json.Marshal(j)
|
dat, _ := json.Marshal(j)
|
||||||
return NewJSONSchemaConverter(propOrder).GrammarFromBytes(dat, maybeArray)
|
return NewJSONSchemaConverter(propOrder).GrammarFromBytes(suffix, dat, maybeArray, maybeString)
|
||||||
}
|
}
|
||||||
|
|
|
@ -8,6 +8,97 @@ import (
|
||||||
. "github.com/onsi/gomega"
|
. "github.com/onsi/gomega"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
var testFunctions = []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"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
var testFunctionsName = []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"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
func rootResult(s string) string {
|
||||||
|
return `root-0-name ::= "\"create_event\""
|
||||||
|
freestring ::= (
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space
|
||||||
|
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 ::= ` + s + `
|
||||||
|
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\""`
|
||||||
|
}
|
||||||
|
|
||||||
const (
|
const (
|
||||||
testInput1 = `
|
testInput1 = `
|
||||||
{
|
{
|
||||||
|
@ -42,6 +133,10 @@ const (
|
||||||
}`
|
}`
|
||||||
|
|
||||||
inputResult1 = `root-0-function ::= "\"create_event\""
|
inputResult1 = `root-0-function ::= "\"create_event\""
|
||||||
|
freestring ::= (
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space
|
||||||
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"function\"" space ":" space root-0-function "}" space
|
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-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
|
||||||
root ::= root-0 | root-1
|
root ::= root-0 | root-1
|
||||||
|
@ -55,6 +150,10 @@ string ::= "\"" (
|
||||||
root-1-function ::= "\"search\""`
|
root-1-function ::= "\"search\""`
|
||||||
|
|
||||||
inputResult2 = `root-0-function ::= "\"create_event\""
|
inputResult2 = `root-0-function ::= "\"create_event\""
|
||||||
|
freestring ::= (
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space
|
||||||
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"function\"" space ":" space root-0-function "}" space
|
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-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
|
||||||
realvalue ::= root-0 | root-1
|
realvalue ::= root-0 | root-1
|
||||||
|
@ -106,6 +205,10 @@ root-1-function ::= "\"search\""`
|
||||||
}`
|
}`
|
||||||
|
|
||||||
inputResult3 = `root-0-name ::= "\"create_event\""
|
inputResult3 = `root-0-name ::= "\"create_event\""
|
||||||
|
freestring ::= (
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space
|
||||||
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"name\"" space ":" space root-0-name "}" space
|
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-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
|
||||||
root ::= root-0 | root-1
|
root ::= root-0 | root-1
|
||||||
|
@ -119,6 +222,10 @@ string ::= "\"" (
|
||||||
root-1-name ::= "\"search\""`
|
root-1-name ::= "\"search\""`
|
||||||
|
|
||||||
inputResult4 = `root-0-name ::= "\"create_event\""
|
inputResult4 = `root-0-name ::= "\"create_event\""
|
||||||
|
freestring ::= (
|
||||||
|
[^"\\] |
|
||||||
|
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||||
|
)* space
|
||||||
root-0 ::= "{" space "\"arguments\"" space ":" space root-0-arguments "," space "\"name\"" space ":" space root-0-name "}" space
|
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-1-arguments ::= "{" space "\"query\"" space ":" space string "}" space
|
||||||
realvalue ::= root-0 | root-1
|
realvalue ::= root-0 | root-1
|
||||||
|
@ -141,7 +248,7 @@ root-1-name ::= "\"search\""`
|
||||||
var _ = Describe("JSON schema grammar tests", func() {
|
var _ = Describe("JSON schema grammar tests", func() {
|
||||||
Context("JSON", func() {
|
Context("JSON", func() {
|
||||||
It("generates a valid grammar from JSON schema", func() {
|
It("generates a valid grammar from JSON schema", func() {
|
||||||
grammar := NewJSONSchemaConverter("").GrammarFromBytes([]byte(testInput1), false)
|
grammar := NewJSONSchemaConverter("").GrammarFromBytes("", []byte(testInput1), false, false)
|
||||||
results := strings.Split(inputResult1, "\n")
|
results := strings.Split(inputResult1, "\n")
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r != "" {
|
if r != "" {
|
||||||
|
@ -151,7 +258,7 @@ var _ = Describe("JSON schema grammar tests", func() {
|
||||||
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))))
|
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))))
|
||||||
})
|
})
|
||||||
It("generates a valid grammar from JSON schema", func() {
|
It("generates a valid grammar from JSON schema", func() {
|
||||||
grammar := NewJSONSchemaConverter("").GrammarFromBytes([]byte(testInput2), false)
|
grammar := NewJSONSchemaConverter("").GrammarFromBytes("", []byte(testInput2), false, false)
|
||||||
results := strings.Split(inputResult3, "\n")
|
results := strings.Split(inputResult3, "\n")
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r != "" {
|
if r != "" {
|
||||||
|
@ -163,40 +270,9 @@ var _ = Describe("JSON schema grammar tests", func() {
|
||||||
It("generates a valid grammar from JSON Objects", func() {
|
It("generates a valid grammar from JSON Objects", func() {
|
||||||
|
|
||||||
structuredGrammar := JSONFunctionStructureFunction{
|
structuredGrammar := JSONFunctionStructureFunction{
|
||||||
OneOf: []ItemFunction{
|
OneOf: testFunctions}
|
||||||
{
|
|
||||||
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)
|
grammar := structuredGrammar.Grammar("", "", false, false)
|
||||||
results := strings.Split(inputResult1, "\n")
|
results := strings.Split(inputResult1, "\n")
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r != "" {
|
if r != "" {
|
||||||
|
@ -208,40 +284,9 @@ var _ = Describe("JSON schema grammar tests", func() {
|
||||||
|
|
||||||
It("generates a valid grammar from JSON Objects for multiple function return", func() {
|
It("generates a valid grammar from JSON Objects for multiple function return", func() {
|
||||||
structuredGrammar := JSONFunctionStructureFunction{
|
structuredGrammar := JSONFunctionStructureFunction{
|
||||||
OneOf: []ItemFunction{
|
OneOf: testFunctions}
|
||||||
{
|
|
||||||
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)
|
grammar := structuredGrammar.Grammar("", "", true, false)
|
||||||
results := strings.Split(inputResult2, "\n")
|
results := strings.Split(inputResult2, "\n")
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r != "" {
|
if r != "" {
|
||||||
|
@ -253,40 +298,9 @@ var _ = Describe("JSON schema grammar tests", func() {
|
||||||
|
|
||||||
It("generates a valid grammar from JSON Objects for multiple function return", func() {
|
It("generates a valid grammar from JSON Objects for multiple function return", func() {
|
||||||
structuredGrammar := JSONFunctionStructureName{
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
OneOf: []ItemName{
|
OneOf: testFunctionsName}
|
||||||
{
|
|
||||||
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)
|
grammar := structuredGrammar.Grammar("", "", true, false)
|
||||||
results := strings.Split(inputResult4, "\n")
|
results := strings.Split(inputResult4, "\n")
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r != "" {
|
if r != "" {
|
||||||
|
@ -295,5 +309,72 @@ var _ = Describe("JSON schema grammar tests", func() {
|
||||||
}
|
}
|
||||||
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))), grammar)
|
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))), grammar)
|
||||||
})
|
})
|
||||||
|
|
||||||
|
It("generates a valid grammar from JSON Objects for multiple function return with a suffix and array", func() {
|
||||||
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
|
OneOf: testFunctionsName}
|
||||||
|
|
||||||
|
grammar := structuredGrammar.Grammar("suffix", "", true, false)
|
||||||
|
results := strings.Split(rootResult(`"suffix" arr | realvalue`), "\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 with a suffix", func() {
|
||||||
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
|
OneOf: testFunctionsName}
|
||||||
|
|
||||||
|
grammar := structuredGrammar.Grammar("suffix", "", false, false)
|
||||||
|
results := strings.Split(rootResult(`"suffix" realvalue`), "\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 with a suffix and could return string", func() {
|
||||||
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
|
OneOf: testFunctionsName}
|
||||||
|
|
||||||
|
grammar := structuredGrammar.Grammar("suffix", "", false, true)
|
||||||
|
results := strings.Split(rootResult(`( "suffix" realvalue | freestring )`), "\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 with a suffix that could return text or an array of tools", func() {
|
||||||
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
|
OneOf: testFunctionsName}
|
||||||
|
|
||||||
|
grammar := structuredGrammar.Grammar("suffix", "", true, true)
|
||||||
|
results := strings.Split(rootResult(`( "suffix" (arr | realvalue) | freestring )`), "\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 without a suffix that could return text or an array of tools or just string", func() {
|
||||||
|
structuredGrammar := JSONFunctionStructureName{
|
||||||
|
OneOf: testFunctionsName}
|
||||||
|
|
||||||
|
grammar := structuredGrammar.Grammar("", "", true, true)
|
||||||
|
results := strings.Split(rootResult(`freestring | arr | realvalue`), "\n")
|
||||||
|
for _, r := range results {
|
||||||
|
if r != "" {
|
||||||
|
Expect(grammar).To(ContainSubstring(r))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Expect(len(results)).To(Equal(len(strings.Split(grammar, "\n"))), grammar)
|
||||||
|
})
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
|
|
|
@ -4,21 +4,49 @@ import (
|
||||||
"encoding/json"
|
"encoding/json"
|
||||||
"fmt"
|
"fmt"
|
||||||
"regexp"
|
"regexp"
|
||||||
|
"strings"
|
||||||
|
|
||||||
"github.com/go-skynet/LocalAI/pkg/utils"
|
"github.com/go-skynet/LocalAI/pkg/utils"
|
||||||
"github.com/rs/zerolog/log"
|
"github.com/rs/zerolog/log"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// FunctionsConfig is the configuration for the tool/function call.
|
||||||
|
// It includes setting to map the function name and arguments from the response
|
||||||
|
// and, for instance, also if processing the requests with BNF grammars.
|
||||||
type FunctionsConfig struct {
|
type FunctionsConfig struct {
|
||||||
|
// DisableNoAction disables the "no action" tool
|
||||||
|
// By default we inject a tool that does nothing and is used to return an answer from the LLM
|
||||||
DisableNoAction bool `yaml:"disable_no_action"`
|
DisableNoAction bool `yaml:"disable_no_action"`
|
||||||
|
|
||||||
|
// NoActionFunctionName is the name of the function that does nothing. It defaults to "answer"
|
||||||
NoActionFunctionName string `yaml:"no_action_function_name"`
|
NoActionFunctionName string `yaml:"no_action_function_name"`
|
||||||
|
|
||||||
|
// NoActionDescriptionName is the name of the function that returns the description of the no action function
|
||||||
NoActionDescriptionName string `yaml:"no_action_description_name"`
|
NoActionDescriptionName string `yaml:"no_action_description_name"`
|
||||||
|
|
||||||
|
// ParallelCalls enables the LLM to return multiple function calls in the same response
|
||||||
ParallelCalls bool `yaml:"parallel_calls"`
|
ParallelCalls bool `yaml:"parallel_calls"`
|
||||||
|
|
||||||
|
// GrammarMessage enables the LLM to return strings and not only JSON objects
|
||||||
|
// This is useful for models to not constraing returning only JSON and also messages back to the user
|
||||||
|
GrammarMessage bool `yaml:"grammar_message"`
|
||||||
|
|
||||||
|
// NoGrammar disables the grammar parsing and parses the responses directly from the LLM
|
||||||
NoGrammar bool `yaml:"no_grammar"`
|
NoGrammar bool `yaml:"no_grammar"`
|
||||||
|
|
||||||
|
// ResponseRegex is a named regex to extract the function name and arguments from the response
|
||||||
ResponseRegex string `yaml:"response_regex"`
|
ResponseRegex string `yaml:"response_regex"`
|
||||||
|
|
||||||
|
// JSONRegexMatch is a regex to extract the JSON object from the response
|
||||||
JSONRegexMatch string `yaml:"json_regex_match"`
|
JSONRegexMatch string `yaml:"json_regex_match"`
|
||||||
|
|
||||||
|
// GrammarPrefix is the suffix to append to the grammar when being generated
|
||||||
|
// This is useful when models prepend a tag before returning JSON
|
||||||
|
GrammarPrefix string `yaml:"grammar_prefix"`
|
||||||
|
|
||||||
|
// ReplaceResults allow to replace strings in the results before parsing them
|
||||||
|
ReplaceResults map[string]string `yaml:"replace_results"`
|
||||||
|
|
||||||
// FunctionName enable the LLM to return { "name": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }
|
// FunctionName enable the LLM to return { "name": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }
|
||||||
// instead of { "function": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }.
|
// instead of { "function": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }.
|
||||||
// This might be useful for certain models trained with the function name as the first token.
|
// This might be useful for certain models trained with the function name as the first token.
|
||||||
|
@ -31,6 +59,15 @@ type FuncCallResults struct {
|
||||||
}
|
}
|
||||||
|
|
||||||
func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncCallResults {
|
func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncCallResults {
|
||||||
|
log.Debug().Msgf("LLM result: %s", llmresult)
|
||||||
|
|
||||||
|
for k, v := range functionConfig.ReplaceResults {
|
||||||
|
log.Debug().Msgf("Replacing %s with %s", k, v)
|
||||||
|
llmresult = strings.ReplaceAll(llmresult, k, v)
|
||||||
|
}
|
||||||
|
|
||||||
|
log.Debug().Msgf("LLM result(processed): %s", llmresult)
|
||||||
|
|
||||||
multipleResults := functionConfig.ParallelCalls
|
multipleResults := functionConfig.ParallelCalls
|
||||||
useGrammars := !functionConfig.NoGrammar
|
useGrammars := !functionConfig.NoGrammar
|
||||||
|
|
||||||
|
@ -48,7 +85,7 @@ func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncC
|
||||||
s = utils.EscapeNewLines(s)
|
s = utils.EscapeNewLines(s)
|
||||||
err := json.Unmarshal([]byte(s), &ss)
|
err := json.Unmarshal([]byte(s), &ss)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
log.Error().Err(err).Str("escapedLLMResult", s).Msg("unable to unmarshal llm result")
|
log.Warn().Err(err).Str("escapedLLMResult", s).Msg("unable to unmarshal llm result")
|
||||||
}
|
}
|
||||||
log.Debug().Msgf("Function return: %s %+v", s, ss)
|
log.Debug().Msgf("Function return: %s %+v", s, ss)
|
||||||
|
|
||||||
|
@ -132,7 +169,7 @@ func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncC
|
||||||
s := utils.EscapeNewLines(llmresult)
|
s := utils.EscapeNewLines(llmresult)
|
||||||
err := json.Unmarshal([]byte(s), &ss)
|
err := json.Unmarshal([]byte(s), &ss)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
log.Error().Err(err).Str("escapedLLMResult", s).Msg("multiple results: unable to unmarshal llm result")
|
log.Warn().Err(err).Str("escapedLLMResult", s).Msg("multiple results: unable to unmarshal llm result")
|
||||||
}
|
}
|
||||||
log.Debug().Msgf("Function return: %s %+v", s, ss)
|
log.Debug().Msgf("Function return: %s %+v", s, ss)
|
||||||
|
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue