update message processing

This commit is contained in:
Michael Yang
2024-06-17 10:38:55 -07:00
parent 78fb33dd07
commit 269ed6e6a2
6 changed files with 685 additions and 720 deletions

View File

@@ -5,6 +5,7 @@ import (
"embed"
"encoding/json"
"errors"
"fmt"
"io"
"math"
"slices"
@@ -14,6 +15,7 @@ import (
"text/template/parse"
"github.com/agnivade/levenshtein"
"github.com/ollama/ollama/api"
"golang.org/x/exp/maps"
)
@@ -74,30 +76,78 @@ func Named(s string) (*named, error) {
return nil, errors.New("no matching template found")
}
var DefaultTemplate, _ = Parse("{{ .Prompt }}")
type Template struct {
*template.Template
raw string
}
var response = parse.ActionNode{
NodeType: parse.NodeAction,
Pipe: &parse.PipeNode{
NodeType: parse.NodePipe,
Cmds: []*parse.CommandNode{
{
NodeType: parse.NodeCommand,
Args: []parse.Node{
&parse.FieldNode{
NodeType: parse.NodeField,
Ident: []string{"Response"},
},
},
},
},
},
}
func Parse(s string) (*Template, error) {
tmpl := template.New("").Option("missingkey=zero").Funcs(template.FuncMap{
"toJson": func(v any) string {
b, err := json.Marshal(v)
if err != nil {
return ""
}
return string(b)
},
"isLastMessage": func(s []*api.Message, m *api.Message) bool {
for i := len(s) - 1; i >= 0; i-- {
if m.Role != s[i].Role {
continue
}
return m == s[i]
}
return false
},
})
tmpl, err := tmpl.Parse(s)
if err != nil {
return nil, err
}
t := Template{Template: tmpl, raw: s}
if vars := t.Vars(); !slices.Contains(vars, "messages") && !slices.Contains(vars, "response") {
// touch up the template and append {{ .Response }}
tmpl.Tree.Root.Nodes = append(tmpl.Tree.Root.Nodes, &response)
}
return &t, nil
}
func (t *Template) String() string {
return t.raw
}
var DefaultTemplate, _ = Parse("{{ .Prompt }}")
func Parse(s string) (*Template, error) {
t, err := template.New("").Option("missingkey=zero").Parse(s)
if err != nil {
return nil, err
}
return &Template{Template: t, raw: s}, nil
}
func (t *Template) Vars() []string {
var vars []string
for _, n := range t.Tree.Root.Nodes {
vars = append(vars, parseNode(n)...)
for _, tt := range t.Templates() {
for _, n := range tt.Root.Nodes {
vars = append(vars, parseNode(n)...)
}
}
set := make(map[string]struct{})
@@ -110,6 +160,97 @@ func (t *Template) Vars() []string {
return vars
}
type Values struct {
Messages []api.Message
}
func (t *Template) Execute(w io.Writer, v Values) error {
system, collated := collate(v.Messages)
if slices.Contains(t.Vars(), "messages") {
return t.Template.Execute(w, map[string]any{
"System": system,
"Messages": collated,
})
}
var b bytes.Buffer
var prompt, response string
for i, m := range collated {
if m.Role == "user" {
prompt = m.Content
} else {
response = m.Content
}
if i != len(collated)-1 && prompt != "" && response != "" {
if err := t.Template.Execute(&b, map[string]any{
"System": "",
"Prompt": prompt,
"Response": response,
}); err != nil {
return err
}
prompt = ""
response = ""
}
}
var cut bool
tree := t.Template.Copy()
// for the last message, cut everything after "{{ .Response }}"
tree.Root.Nodes = slices.DeleteFunc(tree.Root.Nodes, func(n parse.Node) bool {
if slices.Contains(parseNode(n), "Response") {
cut = true
}
return cut
})
if err := template.Must(template.New("").AddParseTree("", tree)).Execute(&b, map[string]any{
"System": system,
"Prompt": prompt,
}); err != nil {
return err
}
_, err := io.Copy(w, &b)
return err
}
func collate(msgs []api.Message) (system string, collated []*api.Message) {
var n int
for i := range msgs {
msg := msgs[i]
if msg.Role == "system" {
if system != "" {
system += "\n\n"
}
system += msg.Content
continue
}
for range msg.Images {
imageTag := fmt.Sprintf("[img-%d]", n)
if !strings.Contains(msg.Content, "[img]") {
msg.Content = strings.TrimSpace("[img] " + msg.Content)
}
msg.Content = strings.Replace(msg.Content, "[img]", imageTag, 1)
n++
}
if len(collated) > 0 && collated[len(collated)-1].Role == msg.Role {
collated[len(collated)-1].Content += "\n\n" + msg.Content
} else {
collated = append(collated, &msg)
}
}
return
}
func parseNode(n parse.Node) []string {
switch n := n.(type) {
case *parse.ActionNode:
@@ -152,6 +293,8 @@ func parseNode(n parse.Node) []string {
return names
case *parse.FieldNode:
return n.Ident
case *parse.TemplateNode:
return parseNode(n.Pipe)
}
return nil

View File

@@ -11,6 +11,7 @@ import (
"testing"
"text/template"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/llm"
)
@@ -64,13 +65,12 @@ func TestParse(t *testing.T) {
template string
vars []string
}{
{"{{ .Prompt }}", []string{"prompt"}},
{"{{ .System }} {{ .Prompt }}", []string{"prompt", "system"}},
{"{{ .Prompt }}", []string{"prompt", "response"}},
{"{{ .System }} {{ .Prompt }}", []string{"prompt", "response", "system"}},
{"{{ .System }} {{ .Prompt }} {{ .Response }}", []string{"prompt", "response", "system"}},
{"{{ with .Tools }}{{ . }}{{ end }} {{ .System }} {{ .Prompt }}", []string{"prompt", "system", "tools"}},
{"{{ with .Tools }}{{ . }}{{ end }} {{ .System }} {{ .Prompt }}", []string{"prompt", "response", "system", "tools"}},
{"{{ range .Messages }}{{ .Role }} {{ .Content }}{{ end }}", []string{"content", "messages", "role"}},
{"{{ range .Messages }}{{ if eq .Role \"system\" }}SYSTEM: {{ .Content }}{{ else if eq .Role \"user\" }}USER: {{ .Content }}{{ else if eq .Role \"assistant\" }}ASSISTANT: {{ .Content }}{{ end }}{{ end }}", []string{"content", "messages", "role"}},
{"{{ .Prompt }} {{ .Suffix }}", []string{"prompt", "suffix"}},
}
for _, tt := range cases {
@@ -87,3 +87,148 @@ func TestParse(t *testing.T) {
})
}
}
func TestExecuteWithMessages(t *testing.T) {
cases := []struct {
templates []string
values Values
expected string
}{
{
[]string{
`[INST] {{ if .System }}{{ .System }}{{ print "\n\n" }}{{ end }}{{ .Prompt }}[/INST] `,
`[INST] {{ if .System }}{{ .System }}{{ print "\n\n" }}{{ end }}{{ .Prompt }}[/INST] {{ .Response }}`,
`{{- range .Messages }}
{{- if eq .Role "user" }}[INST] {{ if and (isLastMessage $.Messages .) $.System }}{{ $.System }}{{ print "\n\n" }}
{{- end }}{{ .Content }}[/INST] {{ else if eq .Role "assistant" }}{{ .Content }}
{{- end }}
{{- end }}`,
},
Values{
Messages: []api.Message{
{Role: "user", Content: "Hello friend!"},
{Role: "assistant", Content: "Hello human!"},
{Role: "user", Content: "Yay!"},
},
},
`[INST] Hello friend![/INST] Hello human![INST] Yay![/INST] `,
},
{
[]string{
`[INST] {{ if .System }}{{ .System }}{{ print "\n\n" }}{{ end }}{{ .Prompt }}[/INST] `,
`[INST] {{ if .System }}{{ .System }}{{ print "\n\n" }}{{ end }}{{ .Prompt }}[/INST] {{ .Response }}`,
`
{{- range .Messages }}
{{- if eq .Role "user" }}[INST] {{ if and (isLastMessage $.Messages .) $.System }}{{ $.System }}{{ print "\n\n" }}
{{- end }}{{ .Content }}[/INST] {{ else if eq .Role "assistant" }}{{ .Content }}
{{- end }}
{{- end }}`,
},
Values{
Messages: []api.Message{
{Role: "system", Content: "You are a helpful assistant!"},
{Role: "user", Content: "Hello friend!"},
{Role: "assistant", Content: "Hello human!"},
{Role: "user", Content: "Yay!"},
},
},
`[INST] Hello friend![/INST] Hello human![INST] You are a helpful assistant!
Yay![/INST] `,
},
{
[]string{
`{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>
`,
`
{{- range .Messages }}
{{- if and (eq .Role "user") (isLastMessage $.Messages .) $.System }}<|im_start|>system
{{ $.System }}<|im_end|>{{ print "\n" }}
{{- end }}<|im_start|>{{ .Role }}
{{ .Content }}<|im_end|>{{ print "\n" }}
{{- end }}<|im_start|>assistant
`,
},
Values{
Messages: []api.Message{
{Role: "system", Content: "You are a helpful assistant!"},
{Role: "user", Content: "Hello friend!"},
{Role: "assistant", Content: "Hello human!"},
{Role: "user", Content: "Yay!"},
},
},
`<|im_start|>user
Hello friend!<|im_end|>
<|im_start|>assistant
Hello human!<|im_end|>
<|im_start|>system
You are a helpful assistant!<|im_end|>
<|im_start|>user
Yay!<|im_end|>
<|im_start|>assistant
`,
},
{
[]string{
`{{ if .Prompt }}Question: {{ .Prompt }}
{{ end }}Answer: {{ .Response }}
`,
`
{{- range .Messages }}
{{- if eq .Role "user" }}Question: {{ .Content }}{{ print "\n\n" }}
{{- else if eq .Role "assistant" }}Answer: {{ .Content }}{{ print "\n\n" }}
{{- end }}
{{- end }}Answer: `,
},
Values{
Messages: []api.Message{
{Role: "user", Content: "What's in this image?", Images: []api.ImageData{[]byte("")}},
{Role: "assistant", Content: "It's a hot dog."},
{Role: "user", Content: "What's in _this_ image?"},
{Role: "user", Images: []api.ImageData{[]byte("")}},
{Role: "user", Content: "Is it a hot dog?"},
},
},
`Question: [img-0] What's in this image?
Answer: It's a hot dog.
Question: What's in _this_ image?
[img-1]
Is it a hot dog?
Answer: `,
},
}
for _, tt := range cases {
t.Run("", func(t *testing.T) {
for _, tmpl := range tt.templates {
t.Run("", func(t *testing.T) {
tmpl, err := Parse(tmpl)
if err != nil {
t.Fatal(err)
}
var b bytes.Buffer
if err := tmpl.Execute(&b, tt.values); err != nil {
t.Fatal(err)
}
if b.String() != tt.expected {
t.Errorf("expected\n%s,\ngot\n%s", tt.expected, b.String())
}
})
}
})
}
}