fix: missing returning error and free callback stream (#187)

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>

Makefile

@@ -3,7 +3,7 @@ GOTEST=$(GOCMD) test
 GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai
 
-GOLLAMA_VERSION?=llama.cpp-f4cef87
+GOLLAMA_VERSION?=2e6ae1269e035886fc64e268a6dda9d8c4ba8c75
 GOGPT4ALLJ_VERSION?=1f7bff57f66cb7062e40d0ac3abd2217815e5109
 GOGPT2_VERSION?=245a5bfe6708ab80dc5c733dcdbfbe3cfd2acdaa
 RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp

README.md

@@ -162,8 +162,6 @@ To build locally, run `make build` (see below).
 
 ### Other examples
 
-![Screenshot from 2023-04-26 23-59-55](https://user-images.githubusercontent.com/2420543/234715439-98d12e03-d3ce-4f94-ab54-2b256808e05e.png)
-
 To see other examples on how to integrate with other projects for instance chatbot-ui, see: [examples](https://github.com/go-skynet/LocalAI/tree/master/examples/).
 
 
@@ -572,7 +570,7 @@ Not currently, as ggml doesn't support GPUs yet: https://github.com/ggerganov/ll
 ### Where is the webUI? 
 
 <details> 
-We are working on to have a good out of the box experience - however as LocalAI is an API you can already plug it into existing projects that provides are UI interfaces to OpenAI's APIs. There are several already on github, and should be compatible with LocalAI already (as it mimics the OpenAI API)
+There is the availability of localai-webui and chatbot-ui in the examples section and can be setup as per the instructions. However as LocalAI is an API you can already plug it into existing projects that provides are UI interfaces to OpenAI's APIs. There are several already on github, and should be compatible with LocalAI already (as it mimics the OpenAI API)
 
 </details>
 

api/openai.go

@@ -299,6 +299,21 @@ func completionEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader,
 }
 
 func chatEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
+
+	process := func(s string, req *OpenAIRequest, config *Config, loader *model.ModelLoader, responses chan OpenAIResponse) {
+		ComputeChoices(s, req, config, loader, func(s string, c *[]Choice) {}, func(s string) bool {
+			resp := OpenAIResponse{
+				Model:   req.Model, // we have to return what the user sent here, due to OpenAI spec.
+				Choices: []Choice{{Delta: &Message{Role: "assistant", Content: s}}},
+				Object:  "chat.completion.chunk",
+			}
+			log.Debug().Msgf("Sending goroutine: %s", s)
+
+			responses <- resp
+			return true
+		})
+		close(responses)
+	}
 	return func(c *fiber.Ctx) error {
 		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
 		if err != nil {
@@ -350,19 +365,7 @@ func chatEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, thread
 		if input.Stream {
 			responses := make(chan OpenAIResponse)
 
-			go func() {
-				ComputeChoices(predInput, input, config, loader, func(s string, c *[]Choice) {}, func(s string) bool {
-					resp := OpenAIResponse{
-						Model:   input.Model, // we have to return what the user sent here, due to OpenAI spec.
-						Choices: []Choice{{Delta: &Message{Role: "assistant", Content: s}}},
-						Object:  "chat.completion.chunk",
-					}
-
-					responses <- resp
-					return true
-				})
-				close(responses)
-			}()
+			go process(predInput, input, config, loader, responses)
 
 			c.Context().SetBodyStreamWriter(fasthttp.StreamWriter(func(w *bufio.Writer) {
 

api/prediction.go

@@ -261,10 +261,15 @@ func ModelInference(s string, loader *model.ModelLoader, c Config, tokenCallback
 				predictOptions = append(predictOptions, llama.SetSeed(c.Seed))
 			}
 
-			return model.Predict(
+			str, er := model.Predict(
 				s,
 				predictOptions...,
 			)
+			// Seems that if we don't free the callback explicitly we leave functions registered (that might try to send on closed channels)
+			// For instance otherwise the API returns: {"error":{"code":500,"message":"send on closed channel","type":""}}
+			// after a stream event has occurred
+			model.SetTokenCallback(nil)
+			return str, er
 		}
 	}
 

examples/README.md

@@ -8,6 +8,7 @@ Here is a list of projects that can easily be integrated with the LocalAI backen
 - [discord-bot](https://github.com/go-skynet/LocalAI/tree/master/examples/discord-bot/) (by [@mudler](https://github.com/mudler))
 - [langchain](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain/) (by [@dave-gray101](https://github.com/dave-gray101))
 - [langchain-python](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain-python/) (by [@mudler](https://github.com/mudler))
+- [localai-webui](https://github.com/go-skynet/LocalAI/tree/master/examples/localai-webui/) (by [@dhruvgera](https://github.com/dhruvgera))
 - [rwkv](https://github.com/go-skynet/LocalAI/tree/master/examples/rwkv/) (by [@mudler](https://github.com/mudler))
 - [slack-bot](https://github.com/go-skynet/LocalAI/tree/master/examples/slack-bot/) (by [@mudler](https://github.com/mudler))
 

examples/localai-webui/README.md

@@ -0,0 +1,26 @@
+# localai-webui
+
+Example of integration with [dhruvgera/localai-frontend](https://github.com/Dhruvgera/LocalAI-frontend).
+
+![image](https://user-images.githubusercontent.com/42107491/235344183-44b5967d-ba22-4331-804c-8da7004a5d35.png)
+
+## Setup
+
+```bash
+# Clone LocalAI
+git clone https://github.com/go-skynet/LocalAI
+
+cd LocalAI/examples/localai-webui
+
+# (optional) Checkout a specific LocalAI tag
+# git checkout -b build <TAG>
+
+# Download any desired models to models/ in the parent LocalAI project dir
+# For example: wget https://gpt4all.io/models/ggml-gpt4all-j.bin
+
+# start with docker-compose
+docker-compose up -d --build
+```
+
+Open http://localhost:3000 for the Web UI.
+

examples/localai-webui/docker-compose.yml

@@ -0,0 +1,20 @@
+version: '3.6'
+
+services:
+  api:
+    image: quay.io/go-skynet/local-ai:latest
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - 8080:8080
+    env_file:
+      - .env
+    volumes:
+      - ./models:/models:cached
+    command: ["/usr/bin/local-ai"]
+
+  frontend:
+    image: quay.io/go-skynet/localai-frontend:master
+    ports:
+      - 3000:3000

go.mod

@@ -3,10 +3,10 @@ module github.com/go-skynet/LocalAI
 go 1.19
 
 require (
-	github.com/donomii/go-rwkv.cpp v0.0.0-20230502223004-0a3db3d72e7d
+	github.com/donomii/go-rwkv.cpp v0.0.0-20230503112711-af62fcc432be
 	github.com/go-skynet/go-gpt2.cpp v0.0.0-20230422085954-245a5bfe6708
 	github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230422090028-1f7bff57f66c
-	github.com/go-skynet/go-llama.cpp v0.0.0-20230502121737-8ceb6167e405
+	github.com/go-skynet/go-llama.cpp v0.0.0-20230503200855-2e6ae1269e03
 	github.com/gofiber/fiber/v2 v2.44.0
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/jaypipes/ghw v0.10.0

go.sum

@@ -14,6 +14,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/donomii/go-rwkv.cpp v0.0.0-20230502223004-0a3db3d72e7d h1:lSHwlYf1H4WAWYgf7rjEVTGen1qmigUq2Egpu8mnQiY=
 github.com/donomii/go-rwkv.cpp v0.0.0-20230502223004-0a3db3d72e7d/go.mod h1:H6QBF7/Tz6DAEBDXQged4H1BvsmqY/K5FG9wQRGa01g=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230503112711-af62fcc432be h1:3Hic97PY6hcw/SY44RuR7kyONkxd744RFeRrqckzwNQ=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230503112711-af62fcc432be/go.mod h1:gWy7FIWioqYmYxkaoFyBnaKApeZVrUkHhv9EV9pz4dM=
 github.com/ghodss/yaml v1.0.0 h1:wQHKEahhL6wmXdzwWG11gIVCkOv05bNOh+Rxn0yngAk=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/go-logr/logr v1.2.3 h1:2DntVwHkVopvECVRSlL5PSo9eG+cAkDCuckLubN+rq0=
@@ -31,6 +33,8 @@ github.com/go-skynet/go-llama.cpp v0.0.0-20230430075552-377fd245eae2 h1:CYQRCbOf
 github.com/go-skynet/go-llama.cpp v0.0.0-20230430075552-377fd245eae2/go.mod h1:35AKIEMY+YTKCBJIa/8GZcNGJ2J+nQk1hQiWo/OnEWw=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230502121737-8ceb6167e405 h1:pbIxJ/eiL1Irdprxk/mquaxjR1XDGCE+7CT9BGJNRaY=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230502121737-8ceb6167e405/go.mod h1:35AKIEMY+YTKCBJIa/8GZcNGJ2J+nQk1hQiWo/OnEWw=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230503200855-2e6ae1269e03 h1:j9fhITFhkz4SczJU0jIaMYo5tdTVTrj+zdhEgWHEr40=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230503200855-2e6ae1269e03/go.mod h1:LvSQx5QAYBAMpWkbyVFFDiM1Tzj8LP55DvmUM3hbRMY=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=

pkg/model/loader.go

@@ -81,10 +81,9 @@ func (ml *ModelLoader) TemplatePrefix(modelName string, in interface{}) (string,
 		if exists {
 			m = t
 		}
-
 	}
 	if m == nil {
-		return "", nil
+		return "", fmt.Errorf("failed loading any template")
 	}
 
 	var buf bytes.Buffer