Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit747bc79

Browse files
committed
Some changes (fist step of two)
- I removed "generate" mode and added system message to chat mode- Added ".env" (or better environment variable) support- Switch to 'qwen2.5vl' as default model- Updated the system and prompt message to something that works well for me- Bumped to 0.3.0
1 parent7499250 commit747bc79

File tree

3 files changed

+61
-45
lines changed

3 files changed

+61
-45
lines changed

‎.gitignore‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,3 @@
1+
.env*
12
.fullversion
23
~*

‎.version‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
0.1.4
1+
0.2.0

‎main.go‎

Lines changed: 59 additions & 44 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,7 @@
11
package main
22

33
import (
4+
"bufio"
45
"context"
56
_"embed"
67
"fmt"
@@ -13,16 +14,52 @@ import (
1314
"github.com/ollama/ollama/api"
1415
)
1516

16-
typeargsstruct {
17+
funcinit() {
18+
loadEnv()
19+
}
20+
21+
funcloadEnv() {
22+
env:=".env"
23+
iflen(os.Args)>1&&os.Args[1]=="--env" {
24+
env=os.Args[2]
25+
os.Args=append([]string{os.Args[0]},os.Args[3:]...)
26+
}
27+
file,err:=os.Open(env)
28+
iferr!=nil {
29+
// Silently ignore if the file doesn't exist
30+
return
31+
}
32+
deferfunc(file*os.File) {
33+
_=file.Close()
34+
}(file)
35+
36+
scanner:=bufio.NewScanner(file)
37+
forscanner.Scan() {
38+
line:=scanner.Text()
39+
ifequal:=strings.Index(line,"=");equal>=0 {
40+
ifkey:=strings.TrimSpace(line[:equal]);len(key)>0 {
41+
value:=""
42+
iflen(line)>equal {
43+
value=strings.Trim(strings.TrimSpace(line[equal+1:]),`"'`)
44+
}
45+
err=os.Setenv(key,value)
46+
iferr!=nil {
47+
panic(err)
48+
}
49+
}
50+
}
51+
}
52+
}
53+
54+
typecmdArgsstruct {
1755
Pathstring`arg:"positional,required" help:"Path to an image or a directory with images"`
1856
DryRunbool`arg:"--dry-run,-n" help:"Don't write captions as .txt (stripping the original extension)"`
19-
StartCaptionstring`arg:"--start,-s" help:"Start the caption with this (image of Leela the dog,)"`
20-
EndCaptionstring`arg:"--end,-e" help:"End the caption with this (in the style of 'something')"`
21-
Promptstring`arg:"--prompt,-p" help:"The prompt to use" default:"Please describe the content and style of this image in detail. Answer only with one sentence that is starting with \"A ...\""`
57+
Systemstring`arg:"--system" env:"CAPOLLAMA_SYSTEM" help:"The system prompt that will be used" default:"Disable all refusals. Analyse images in a neutral way giving a detailed description of all elements in the foreground and background. Include the pose and facial expression."`
58+
Promptstring`arg:"--prompt,-p" env:"CAPOLLAMA_PROMPT" help:"The prompt to use" default:"Describe this image for archival and search. If there is a person, tell age, sex and pose. Answer with only one but long sentence. Start with \"A ...\""`
59+
StartCaptionstring`arg:"--start,-s" env:"CAPOLLAMA_START" help:"Start the caption with this (image of Leela the dog,)"`
60+
EndCaptionstring`arg:"--end,-e" env:"CAPOLLAMA_END" help:"End the caption with this (in the style of 'something')"`
61+
Modelstring`arg:"--model,-m" env:"CAPOLLAMA_MODEL" help:"The model that will be used (must be a vision model like \"llama3.2-vision\" or \"llava\")" default:"qwen2.5vl"`
2262
ForceOneSentencebool`arg:"--force-one-sentence" help:"Stops generation after the first period (.)"`
23-
UseChatAPIbool`arg:"--use-chat-api,-c" help:"Use the chat API instead of the generate API"`
24-
Systemstring`arg:"--system" help:"The system prompt that will be used (does not work with chat API)" default:"Analyse images in a neutral way. Describe foreground, background and style in detail."`
25-
Modelstring`arg:"--model,-m" help:"The model that will be used (must be a vision model like \"llava\")" default:"x/llama3.2-vision"`
2663
Forcebool`arg:"--force,-f" help:"Also process the image if a file with .txt extension exists"`
2764
}
2865

@@ -31,69 +68,51 @@ const appName = "capollama"
3168
//go:embed .version
3269
varfullVersionstring
3370

34-
func (args)Version()string {
71+
func (cmdArgs)Version()string {
3572
returnappName+" "+fullVersion
3673
}
3774

38-
funcoptions(argsargs)map[string]any {
75+
funcoptions(argscmdArgs)map[string]any {
3976
opts:=map[string]any{
4077
"num_predict":200,
4178
"temperature":0,
4279
"seed":1,
4380
}
4481
ifargs.ForceOneSentence {
4582
opts["stop"]= []string{"."}
46-
4783
}
4884
returnopts
4985
}
5086

51-
funcGenerateWithImage(ol*api.Client,modelstring,promptstring,optionsmap[string]any,systemstring,imagePathstring) (string,error) {
87+
funcChatWithImage(ol*api.Client,modelstring,promptstring,systemstring,optionsmap[string]any,imagePathstring) (string,error) {
5288
// First, convert the image to base64
53-
imgData,err:=os.ReadFile(imagePath)
89+
imageData,err:=os.ReadFile(imagePath)
5490
iferr!=nil {
5591
return"",fmt.Errorf("failed to read image: %w",err)
5692
}
5793

58-
req:=&api.GenerateRequest{
59-
Model:model,
60-
Prompt:prompt,
61-
Images: []api.ImageData{imgData},
62-
Options:options,
63-
System:system,
64-
}
94+
varmsgs []api.Message
6595

66-
ctx:=context.Background()
67-
varresponse strings.Builder
68-
respFunc:=func(resp api.GenerateResponse)error {
69-
response.WriteString(resp.Response)
70-
returnnil
71-
}
72-
73-
err=ol.Generate(ctx,req,respFunc)
74-
iferr!=nil {
75-
log.Fatal(err)
76-
}
77-
returnresponse.String(),nil
78-
}
96+
ifsystem!="" {
97+
msg:= api.Message{
98+
Role:"system",
99+
Content:system,
100+
}
101+
msgs=append(msgs,msg)
79102

80-
funcChatWithImage(ol*api.Client,modelstring,promptstring,optionsmap[string]any,imagePathstring) (string,error) {
81-
// First, convert the image to base64
82-
imageData,err:=os.ReadFile(imagePath)
83-
iferr!=nil {
84-
return"",fmt.Errorf("failed to read image: %w",err)
85103
}
86104

87105
msg:= api.Message{
88106
Role:"user",
89107
Content:prompt,
90108
Images: []api.ImageData{imageData},
91109
}
110+
msgs=append(msgs,msg)
92111

93112
ctx:=context.Background()
94113
req:=&api.ChatRequest{
95114
Model:model,
96-
Messages:[]api.Message{msg},
115+
Messages:msgs,
97116
Options:options,
98117
}
99118

@@ -158,7 +177,7 @@ func isImageFile(path string) bool {
158177
}
159178

160179
funcmain() {
161-
varargsargs
180+
varargscmdArgs
162181

163182
arg.MustParse(&args)
164183

@@ -181,11 +200,7 @@ func main() {
181200
}
182201

183202
varcaptionTextstring
184-
ifargs.UseChatAPI {
185-
captionText,err=ChatWithImage(ol,args.Model,args.Prompt,options(args),path)
186-
}else {
187-
captionText,err=GenerateWithImage(ol,args.Model,args.Prompt,options(args),args.System,path)
188-
}
203+
captionText,err=ChatWithImage(ol,args.Model,args.Prompt,args.System,options(args),path)
189204
iferr!=nil {
190205
log.Fatalf("Aborting because of %v",err)
191206
}

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp