mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-17 08:15:00 +00:00
feat: Add backend gallery (#5607)
* feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto
GitHub
parent
a7a6020328
commit
2d64269763
114 changed files with 3996 additions and 1382 deletions
|
|
@ -485,29 +485,6 @@ var _ = Describe("API test", func() {
|
|||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(content["backend"]).To(Equal("llama"))
|
||||
})
|
||||
It("apply models from config", func() {
|
||||
response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
|
||||
ConfigURL: "https://raw.githubusercontent.com/mudler/LocalAI/v2.25.0/embedded/models/hermes-2-pro-mistral.yaml",
|
||||
})
|
||||
|
||||
Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
|
||||
|
||||
uuid := response["uuid"].(string)
|
||||
|
||||
Eventually(func() bool {
|
||||
response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
|
||||
return response["processed"].(bool)
|
||||
}, "900s", "10s").Should(Equal(true))
|
||||
|
||||
Eventually(func() []string {
|
||||
models, _ := client.ListModels(context.TODO())
|
||||
modelList := []string{}
|
||||
for _, m := range models.Models {
|
||||
modelList = append(modelList, m.ID)
|
||||
}
|
||||
return modelList
|
||||
}, "360s", "10s").Should(ContainElements("hermes-2-pro-mistral"))
|
||||
})
|
||||
It("apply models without overrides", func() {
|
||||
response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
|
||||
URL: bertEmbeddingsURL,
|
||||
|
|
@ -533,80 +510,6 @@ var _ = Describe("API test", func() {
|
|||
Expect(content["usage"]).To(ContainSubstring("You can test this model with curl like this"))
|
||||
})
|
||||
|
||||
It("runs openllama gguf(llama-cpp)", Label("llama-gguf"), func() {
|
||||
if runtime.GOOS != "linux" {
|
||||
Skip("test supported only on linux")
|
||||
}
|
||||
|
||||
modelName := "hermes-2-pro-mistral"
|
||||
response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
|
||||
ConfigURL: "https://raw.githubusercontent.com/mudler/LocalAI/v2.25.0/embedded/models/hermes-2-pro-mistral.yaml",
|
||||
})
|
||||
|
||||
Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
|
||||
|
||||
uuid := response["uuid"].(string)
|
||||
|
||||
Eventually(func() bool {
|
||||
response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
|
||||
return response["processed"].(bool)
|
||||
}, "900s", "10s").Should(Equal(true))
|
||||
|
||||
By("testing chat")
|
||||
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: modelName, Messages: []openai.ChatCompletionMessage{
|
||||
{
|
||||
Role: "user",
|
||||
Content: "How much is 2+2?",
|
||||
},
|
||||
}})
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(resp.Choices)).To(Equal(1))
|
||||
Expect(resp.Choices[0].Message.Content).To(Or(ContainSubstring("4"), ContainSubstring("four")))
|
||||
|
||||
By("testing functions")
|
||||
resp2, err := client.CreateChatCompletion(
|
||||
context.TODO(),
|
||||
openai.ChatCompletionRequest{
|
||||
Model: modelName,
|
||||
Messages: []openai.ChatCompletionMessage{
|
||||
{
|
||||
Role: "user",
|
||||
Content: "What is the weather like in San Francisco (celsius)?",
|
||||
},
|
||||
},
|
||||
Functions: []openai.FunctionDefinition{
|
||||
openai.FunctionDefinition{
|
||||
Name: "get_current_weather",
|
||||
Description: "Get the current weather",
|
||||
Parameters: jsonschema.Definition{
|
||||
Type: jsonschema.Object,
|
||||
Properties: map[string]jsonschema.Definition{
|
||||
"location": {
|
||||
Type: jsonschema.String,
|
||||
Description: "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
"unit": {
|
||||
Type: jsonschema.String,
|
||||
Enum: []string{"celcius", "fahrenheit"},
|
||||
},
|
||||
},
|
||||
Required: []string{"location"},
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(resp2.Choices)).To(Equal(1))
|
||||
Expect(resp2.Choices[0].Message.FunctionCall).ToNot(BeNil())
|
||||
Expect(resp2.Choices[0].Message.FunctionCall.Name).To(Equal("get_current_weather"), resp2.Choices[0].Message.FunctionCall.Name)
|
||||
|
||||
var res map[string]string
|
||||
err = json.Unmarshal([]byte(resp2.Choices[0].Message.FunctionCall.Arguments), &res)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(res["location"]).To(ContainSubstring("San Francisco"), fmt.Sprint(res))
|
||||
Expect(res["unit"]).To(Equal("celcius"), fmt.Sprint(res))
|
||||
Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
|
|
@ -673,6 +576,82 @@ var _ = Describe("API test", func() {
|
|||
_, err = os.ReadDir(tmpdir)
|
||||
Expect(err).To(HaveOccurred())
|
||||
})
|
||||
|
||||
It("runs gguf models (chat)", Label("llama-gguf"), func() {
|
||||
if runtime.GOOS != "linux" {
|
||||
Skip("test supported only on linux")
|
||||
}
|
||||
|
||||
modelName := "qwen3-1.7b"
|
||||
response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
|
||||
ID: "localai@" + modelName,
|
||||
})
|
||||
|
||||
Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
|
||||
|
||||
uuid := response["uuid"].(string)
|
||||
|
||||
Eventually(func() bool {
|
||||
response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
|
||||
return response["processed"].(bool)
|
||||
}, "900s", "10s").Should(Equal(true))
|
||||
|
||||
By("testing chat")
|
||||
resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: modelName, Messages: []openai.ChatCompletionMessage{
|
||||
{
|
||||
Role: "user",
|
||||
Content: "How much is 2+2?",
|
||||
},
|
||||
}})
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(resp.Choices)).To(Equal(1))
|
||||
Expect(resp.Choices[0].Message.Content).To(Or(ContainSubstring("4"), ContainSubstring("four")))
|
||||
|
||||
By("testing functions")
|
||||
resp2, err := client.CreateChatCompletion(
|
||||
context.TODO(),
|
||||
openai.ChatCompletionRequest{
|
||||
Model: modelName,
|
||||
Messages: []openai.ChatCompletionMessage{
|
||||
{
|
||||
Role: "user",
|
||||
Content: "What is the weather like in San Francisco (celsius)?",
|
||||
},
|
||||
},
|
||||
Functions: []openai.FunctionDefinition{
|
||||
openai.FunctionDefinition{
|
||||
Name: "get_current_weather",
|
||||
Description: "Get the current weather",
|
||||
Parameters: jsonschema.Definition{
|
||||
Type: jsonschema.Object,
|
||||
Properties: map[string]jsonschema.Definition{
|
||||
"location": {
|
||||
Type: jsonschema.String,
|
||||
Description: "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
"unit": {
|
||||
Type: jsonschema.String,
|
||||
Enum: []string{"celcius", "fahrenheit"},
|
||||
},
|
||||
},
|
||||
Required: []string{"location"},
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(len(resp2.Choices)).To(Equal(1))
|
||||
Expect(resp2.Choices[0].Message.FunctionCall).ToNot(BeNil())
|
||||
Expect(resp2.Choices[0].Message.FunctionCall.Name).To(Equal("get_current_weather"), resp2.Choices[0].Message.FunctionCall.Name)
|
||||
|
||||
var res map[string]string
|
||||
err = json.Unmarshal([]byte(resp2.Choices[0].Message.FunctionCall.Arguments), &res)
|
||||
Expect(err).ToNot(HaveOccurred())
|
||||
Expect(res["location"]).To(ContainSubstring("San Francisco"), fmt.Sprint(res))
|
||||
Expect(res["unit"]).To(Equal("celcius"), fmt.Sprint(res))
|
||||
Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
|
||||
})
|
||||
|
||||
It("installs and is capable to run tts", Label("tts"), func() {
|
||||
if runtime.GOOS != "linux" {
|
||||
Skip("test supported only on linux")
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue