ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-17 06:28:07 +00:00
Code Issues Actions 24 Packages Projects Releases Wiki Activity

feat: Use ubuntu as base for container images, drop deprecated ggml-transformers backends (#1689)

Browse Source 
* cleanup backends

* switch image to ubuntu 22.04

* adapt commands for ubuntu

* transformers cleanup

* no contrib on ubuntu

* Change test model to gguf

* ci: disable bark tests (too cpu-intensive)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* cleanup

* refinements

* use intel base image

* Makefile: Add docker targets

* Change test model

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2024-02-08 20:12:51 +01:00
committed by GitHub
parent d0a6a35b55
commit ddd21f1644
20 changed files with 161 additions and 466 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
api/api_test.go
View File

@ -29,6 +29,15 @@ import (
"github.com/sashabaranov/go-openai/jsonschema"
)
const testPrompt = `### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
Can you help rephrasing sentences?
### Response:`
type modelApplyRequest struct {
ID string `json:"id"`
URL string `json:"url"`
@ -629,28 +638,28 @@ var _ = Describe("API test", func() {
Expect(len(models.Models)).To(Equal(6)) // If "config.yaml" should be included, this should be 8?
})
It("can generate completions", func() {
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "testmodel", Prompt: "abcdedfghikl"})
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "testmodel", Prompt: testPrompt})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Text).ToNot(BeEmpty())
})
It("can generate chat completions ", func() {
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "testmodel", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "abcdedfghikl"}}})
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "testmodel", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: testPrompt}}})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
})
It("can generate completions from model configs", func() {
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "gpt4all", Prompt: "abcdedfghikl"})
resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "gpt4all", Prompt: testPrompt})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Text).ToNot(BeEmpty())
})
It("can generate chat completions from model configs", func() {
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "gpt4all-2", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "abcdedfghikl"}}})
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "gpt4all-2", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: testPrompt}}})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
@ -658,7 +667,7 @@ var _ = Describe("API test", func() {
It("returns errors", func() {
backends := len(model.AutoLoadBackends) + 1 // +1 for huggingface
_, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "foomodel", Prompt: "abcdedfghikl"})
_, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "foomodel", Prompt: testPrompt})
Expect(err).To(HaveOccurred())
Expect(err.Error()).To(ContainSubstring(fmt.Sprintf("error, status code: 500, message: could not load model - all backends returned error: %d errors occurred:", backends)))
})
@ -834,13 +843,13 @@ var _ = Describe("API test", func() {
app.Shutdown()
})
It("can generate chat completions from config file (list1)", func() {
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list1", Messages: []openai.ChatCompletionMessage{{Role: "user", Content: "abcdedfghikl"}}})
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list1", Messages: []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}}})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
})
It("can generate chat completions from config file (list2)", func() {
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list2", Messages: []openai.ChatCompletionMessage{{Role: "user", Content: "abcdedfghikl"}}})
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list2", Messages: []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}}})
Expect(err).ToNot(HaveOccurred())
Expect(len(resp.Choices)).To(Equal(1))
Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())