Minor fixes (#285 )

⬆️ Update go-skynet/go-bert.cpp (#274 )
Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>
2026-02-03 03:02:38 -05:00 · 2023-05-17 21:01:46 +02:00 · 2023-05-17 11:56:32 +02:00 · 2023-05-17 11:52:54 +02:00 · 2023-05-17 11:52:37 +02:00 · 2023-05-17 09:47:22 +02:00
36 changed files with 1041 additions and 139 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -1,2 +1,4 @@
 models
-examples/chatbot-ui/models
+examples/chatbot-ui/models
+examples/rwkv/models
+examples/**/models
--- a/.github/workflows/bump_deps.yaml
+++ b/.github/workflows/bump_deps.yaml
@@ -9,9 +9,6 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - repository: "go-skynet/go-gpt4all-j.cpp"
-            variable: "GOGPT4ALLJ_VERSION"
-            branch: "master"
          - repository: "go-skynet/go-llama.cpp"
            variable: "GOLLAMA_VERSION"
            branch: "master"
@@ -30,7 +27,7 @@ jobs:
          - repository: "go-skynet/bloomz.cpp"
            variable: "BLOOMZ_VERSION"
            branch: "main"
-          - repository: "go-skynet/gpt4all"
+          - repository: "nomic-ai/gpt4all"
            variable: "GPT4ALL_VERSION"
            branch: "main"
    runs-on: ubuntu-latest
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -21,7 +21,7 @@ jobs:
      - name: Dependencies
        run: |
          sudo apt-get update
-          sudo apt-get install build-essential
+          sudo apt-get install build-essential ffmpeg
      - name: Test
        run: |
          make test
@@ -38,7 +38,7 @@ jobs:
      - name: Dependencies
        run: |
          brew update
-          brew install sdl2
+          brew install sdl2 ffmpeg
      - name: Test
        run: |
          make test
--- a/.gitignore
+++ b/.gitignore
@@ -1,6 +1,7 @@
 # go-llama build artifacts
 go-llama
-go-gpt4all-j
+gpt4all
+go-stable-diffusion
 go-gpt2
 go-rwkv
 whisper.cpp
--- a/3
+++ b/3
@@ -2,8 +2,9 @@ ARG GO_VERSION=1.20
 ARG BUILD_TYPE=
 FROM golang:$GO_VERSION
 WORKDIR /build
-RUN apt-get update && apt-get install -y cmake
+RUN apt-get update && apt-get install -y cmake libgomp1 libopenblas-dev libopenblas-base libopencv-dev libopencv-core-dev libopencv-core4.5 
 COPY . .
+RUN ln -s /usr/include/opencv4/opencv2/ /usr/include/opencv2
 RUN make prepare-sources
 EXPOSE 8080
 ENTRYPOINT [ "/build/entrypoint.sh" ]
--- a/Dockerfile.dev
+++ b/Dockerfile.dev
@@ -4,7 +4,8 @@ ARG BUILD_TYPE=

 FROM golang:$GO_VERSION as builder
 WORKDIR /build
-RUN apt-get update && apt-get install -y cmake
+RUN apt-get update && apt-get install -y cmake libgomp1 libopenblas-dev libopenblas-base libopencv-dev libopencv-core-dev libopencv-core4.5 
+RUN ln -s /usr/include/opencv4/opencv2/ /usr/include/opencv2
 COPY . .
 RUN make build

--- a/79
+++ b/79
@@ -3,16 +3,23 @@ GOTEST=$(GOCMD) test
 GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai

-GOLLAMA_VERSION?=c03e8adbc45c866e0f6d876af1887d6b01d57eb4
-GPT4ALL_REPO?=https://github.com/go-skynet/gpt4all
-GPT4ALL_VERSION?=3657f9417e17edf378c27d0a9274a1bf41caa914
-GOGPT2_VERSION?=6a10572
+GOLLAMA_VERSION?=7f9ae4246088f0c08ed322acbae21d69cd2eb547
+GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
+GPT4ALL_VERSION?=a07237e54fcdfdb351913587052ac061a2a7bdff
+GOGPT2_VERSION?=7bff56f0224502c1c9ed6258d2a17e8084628827
 RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp
 RWKV_VERSION?=07166da10cb2a9e8854395a4f210464dcea76e47
-WHISPER_CPP_VERSION?=bf2449dfae35a46b2cd92ab22661ce81a48d4993
-BERT_VERSION?=ec771ec715576ac050263bb7bb74bfd616a5ba13
+WHISPER_CPP_VERSION?=95b02d76b04d18e4ce37ed8353a1f0797f1717ea
+BERT_VERSION?=cea1ed76a7f48ef386a8e369f6c82c48cdf2d551
 BLOOMZ_VERSION?=e9366e82abdfe70565644fbfae9651976714efd1
+BUILD_TYPE?=
+CGO_LDFLAGS?=
+CUDA_LIBPATH?=/usr/local/cuda/lib64/
+STABLEDIFFUSION_VERSION?=c0748eca3642d58bcf9521108bcee46959c647dc

+GO_TAGS?=
+
+OPTIONAL_TARGETS?=

 GREEN  := $(shell tput -Txterm setaf 2)
 YELLOW := $(shell tput -Txterm setaf 3)
@@ -20,18 +27,20 @@ WHITE  := $(shell tput -Txterm setaf 7)
 CYAN   := $(shell tput -Txterm setaf 6)
 RESET  := $(shell tput -Txterm sgr0)

-C_INCLUDE_PATH=$(shell pwd)/go-llama:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
-LIBRARY_PATH=$(shell pwd)/go-llama:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
+C_INCLUDE_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz
+LIBRARY_PATH=$(shell pwd)/go-llama:$(shell pwd)/go-stable-diffusion/:$(shell pwd)/gpt4all/gpt4all-bindings/golang/:$(shell pwd)/go-gpt2:$(shell pwd)/go-rwkv:$(shell pwd)/whisper.cpp:$(shell pwd)/go-bert:$(shell pwd)/bloomz

-# Use this if you want to set the default behavior
-ifndef BUILD_TYPE
-	BUILD_TYPE:=default
+ifeq ($(BUILD_TYPE),openblas)
+	CGO_LDFLAGS+=-lopenblas
 endif

-ifeq ($(BUILD_TYPE), "generic")
-	GENERIC_PREFIX:=generic-
-else
-	GENERIC_PREFIX:=
+ifeq ($(BUILD_TYPE),cublas)
+	CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH)
+endif
+
+
+ifeq ($(GO_TAGS),stablediffusion)
+	OPTIONAL_TARGETS+=go-stable-diffusion/libstablediffusion.a
 endif

 .PHONY: all test build vendor
@@ -67,6 +76,14 @@ go-bert:
 	@find ./go-bert -type f -name "*.cpp" -exec sed -i'' -e 's/ggml_/ggml_bert_/g' {} +
 	@find ./go-bert -type f -name "*.h" -exec sed -i'' -e 's/ggml_/ggml_bert_/g' {} +

+## stable diffusion
+go-stable-diffusion:
+	git clone --recurse-submodules https://github.com/mudler/go-stable-diffusion go-stable-diffusion
+	cd go-stable-diffusion && git checkout -b build $(STABLEDIFFUSION_VERSION) && git submodule update --init --recursive --depth 1
+
+go-stable-diffusion/libstablediffusion.a:
+	$(MAKE) -C go-stable-diffusion libstablediffusion.a
+
 ## RWKV
 go-rwkv:
 	git clone --recurse-submodules $(RWKV_REPO) go-rwkv
@@ -94,7 +111,7 @@ go-bert/libgobert.a: go-bert
 	$(MAKE) -C go-bert libgobert.a

 gpt4all/gpt4all-bindings/golang/libgpt4all.a: gpt4all
-	$(MAKE) -C gpt4all/gpt4all-bindings/golang/ $(GENERIC_PREFIX)libgpt4all.a
+	$(MAKE) -C gpt4all/gpt4all-bindings/golang/ libgpt4all.a

 ## CEREBRAS GPT
 go-gpt2: 
@@ -113,11 +130,14 @@ go-gpt2:
 	@find ./go-gpt2 -type f -name "*.cpp" -exec sed -i'' -e 's/json_/json_gpt2_/g' {} +

 go-gpt2/libgpt2.a: go-gpt2
-	$(MAKE) -C go-gpt2 $(GENERIC_PREFIX)libgpt2.a
+	$(MAKE) -C go-gpt2 libgpt2.a

 whisper.cpp:
 	git clone https://github.com/ggerganov/whisper.cpp.git
 	cd whisper.cpp && git checkout -b build $(WHISPER_CPP_VERSION) && git submodule update --init --recursive --depth 1
+	@find ./whisper.cpp -type f -name "*.c" -exec sed -i'' -e 's/ggml_/ggml_whisper_/g' {} +
+	@find ./whisper.cpp -type f -name "*.cpp" -exec sed -i'' -e 's/ggml_/ggml_whisper_/g' {} +
+	@find ./whisper.cpp -type f -name "*.h" -exec sed -i'' -e 's/ggml_/ggml_whisper_/g' {} +

 whisper.cpp/libwhisper.a: whisper.cpp
 	cd whisper.cpp && make libwhisper.a
@@ -127,18 +147,19 @@ go-llama:
 	cd go-llama && git checkout -b build $(GOLLAMA_VERSION) && git submodule update --init --recursive --depth 1

 go-llama/libbinding.a: go-llama 
-	$(MAKE) -C go-llama $(GENERIC_PREFIX)libbinding.a
+	$(MAKE) -C go-llama BUILD_TYPE=$(BUILD_TYPE) libbinding.a

 replace:
 	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/go-llama
-	$(GOCMD) mod edit -replace github.com/nomic/gpt4all/gpt4all-bindings/golang=$(shell pwd)/gpt4all/gpt4all-bindings/golang
+	$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(shell pwd)/gpt4all/gpt4all-bindings/golang
 	$(GOCMD) mod edit -replace github.com/go-skynet/go-gpt2.cpp=$(shell pwd)/go-gpt2
 	$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(shell pwd)/go-rwkv
 	$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(shell pwd)/whisper.cpp
 	$(GOCMD) mod edit -replace github.com/go-skynet/go-bert.cpp=$(shell pwd)/go-bert
 	$(GOCMD) mod edit -replace github.com/go-skynet/bloomz.cpp=$(shell pwd)/bloomz
+	$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(shell pwd)/go-stable-diffusion

-prepare-sources: go-llama go-gpt2 gpt4all go-rwkv whisper.cpp go-bert bloomz replace
+prepare-sources: go-llama go-gpt2 gpt4all go-rwkv whisper.cpp go-bert bloomz go-stable-diffusion replace
 	$(GOCMD) mod download

 ## GENERIC
@@ -148,19 +169,22 @@ rebuild: ## Rebuilds the project
 	$(MAKE) -C go-gpt2 clean
 	$(MAKE) -C go-rwkv clean
 	$(MAKE) -C whisper.cpp clean
+	$(MAKE) -C go-stable-diffusion clean
 	$(MAKE) -C go-bert clean
 	$(MAKE) -C bloomz clean
 	$(MAKE) build

-prepare: prepare-sources gpt4all/gpt4all-bindings/golang/libgpt4all.a go-llama/libbinding.a go-bert/libgobert.a go-gpt2/libgpt2.a go-rwkv/librwkv.a whisper.cpp/libwhisper.a bloomz/libbloomz.a  ## Prepares for building
+prepare: prepare-sources gpt4all/gpt4all-bindings/golang/libgpt4all.a $(OPTIONAL_TARGETS) go-llama/libbinding.a go-bert/libgobert.a go-gpt2/libgpt2.a go-rwkv/librwkv.a whisper.cpp/libwhisper.a bloomz/libbloomz.a  ## Prepares for building

 clean: ## Remove build related file
 	rm -fr ./go-llama
 	rm -rf ./gpt4all
+	rm -rf ./go-stable-diffusion
 	rm -rf ./go-gpt2
 	rm -rf ./go-rwkv
 	rm -rf ./go-bert
 	rm -rf ./bloomz
+	rm -rf ./whisper.cpp
 	rm -rf $(BINARY_NAME)

 ## Build:
@@ -168,23 +192,30 @@ clean: ## Remove build related file
 build: prepare ## Build the project
 	$(info ${GREEN}I local-ai build info:${RESET})
 	$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
-	C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} $(GOCMD) build -x -o $(BINARY_NAME) ./
+	$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} $(GOCMD) build -tags "$(GO_TAGS)" -x -o $(BINARY_NAME) ./

 generic-build: ## Build the project using generic
 	BUILD_TYPE="generic" $(MAKE) build

 ## Run
 run: prepare ## run local-ai
-	C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} $(GOCMD) run ./main.go
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} $(GOCMD) run ./main.go

 test-models/testmodel:
 	mkdir test-models
+	mkdir test-dir
 	wget https://huggingface.co/concedo/cerebras-111M-ggml/resolve/main/cerberas-111m-q4_0.bin -O test-models/testmodel
+	wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
+	wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O test-models/bert
+	wget https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
+	wget https://huggingface.co/imxcstar/rwkv-4-raven-ggml/resolve/main/RWKV-4-Raven-1B5-v11-Eng99%25-Other1%25-20230425-ctx4096-16_Q4_2.bin -O test-models/rwkv
+	wget https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json -O test-models/rwkv.tokenizer.json
 	cp tests/fixtures/* test-models

 test: prepare test-models/testmodel
 	cp tests/fixtures/* test-models
-	@C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models $(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo -v -r ./api
+	@C_INCLUDE_PATH=${C_INCLUDE_PATH} LIBRARY_PATH=${LIBRARY_PATH} TEST_DIR=$(abspath ./)/test-dir/ CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models $(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo -v -r ./api

 ## Help:
 help: ## Show this help.
--- a/README.md
+++ b/README.md
@@ -9,13 +9,13 @@

 [![](https://dcbadge.vercel.app/api/server/uJAeKSAGDy?style=flat-square&theme=default-inverted)](https://discord.gg/uJAeKSAGDy) 

-**LocalAI** is a drop-in replacement REST API compatible with OpenAI for local CPU inferencing. It allows to run models locally or on-prem with consumer grade hardware, supporting multiple models families. Supports also GPT4ALL-J which is licensed under Apache 2.0.
+**LocalAI** is a drop-in replacement REST API compatible with OpenAI API specifications for local inferencing. It allows to run models locally or on-prem with consumer grade hardware, supporting multiple models families compatible with the `ggml` format. For a list of the supported model families, see [the model compatibility table below](https://github.com/go-skynet/LocalAI#model-compatibility-table).

- OpenAI compatible API
- Supports multiple models
+- OpenAI drop-in alternative REST API
+- Supports multiple models, Audio transcription, Text generation with GPTs, Image generation with stable diffusion (experimental)
 - Once loaded the first time, it keep models loaded in memory for faster inference
 - Support for prompt templates
- Doesn't shell-out, but uses C bindings for a faster inference and better performance. 
+- Doesn't shell-out, but uses C++ bindings for a faster inference and better performance. 

 LocalAI is a community-driven project, focused on making the AI accessible to anyone. Any contribution, feedback and PR is welcome! It was initially created by [mudler](https://github.com/mudler/) at the [SpectroCloud OSS Office](https://github.com/spectrocloud).

@@ -23,10 +23,30 @@ LocalAI uses C++ bindings for optimizing speed. It is based on [llama.cpp](https

 See [examples on how to integrate LocalAI](https://github.com/go-skynet/LocalAI/tree/master/examples/).

+
+### How does it work?  
+
+<details>
+  
+![LocalAI](https://github.com/go-skynet/LocalAI/assets/2420543/38de3a9b-3866-48cd-9234-662f9571064a)
+
+</details>
+
 ## News

- 11-05-2023: __1.9.0__ released! 🔥 Important whisper updates ( https://github.com/go-skynet/LocalAI/pull/233 https://github.com/go-skynet/LocalAI/pull/229 ) and extended gpt4all model families support ( https://github.com/go-skynet/LocalAI/pull/232 ). Redpajama/dolly experimental ( https://github.com/go-skynet/LocalAI/pull/214 )
- 10-05-2023: __1.8.0__ released! 🔥 Added support for fast and accurate embeddings with `bert.cpp` ( https://github.com/go-skynet/LocalAI/pull/222 )
+- 16-05-2023: 🔥🔥🔥 Experimental support for CUDA (https://github.com/go-skynet/LocalAI/pull/258) in the `llama.cpp` backend and Stable diffusion CPU image generation (https://github.com/go-skynet/LocalAI/pull/272) in `master`.
+
+Now LocalAI can generate images too:
+
+| mode=0                                                                                                                | mode=1 (winograd/sgemm)                                                                                                                |
+|------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------|
+| ![b6441997879](https://github.com/go-skynet/LocalAI/assets/2420543/d50af51c-51b7-4f39-b6c2-bf04c403894c)              | ![winograd2](https://github.com/go-skynet/LocalAI/assets/2420543/1935a69a-ecce-4afc-a099-1ac28cb649b3)                |
+
+- 14-05-2023: __v1.11.1__ released! `rwkv` backend patch release
+- 13-05-2023: __v1.11.0__ released! 🔥 Updated `llama.cpp` bindings: This update includes a breaking change in the model files ( https://github.com/ggerganov/llama.cpp/pull/1405 ) - old models should still work with the `gpt4all-llama` backend.
+- 12-05-2023: __v1.10.0__ released! 🔥🔥 Updated `gpt4all` bindings. Added support for GPTNeox (experimental), RedPajama (experimental), Starcoder (experimental), Replit (experimental), MosaicML MPT. Also now `embeddings` endpoint supports tokens arrays. See the [langchain-chroma](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain-chroma) example! Note - this update does NOT include https://github.com/ggerganov/llama.cpp/pull/1405 which makes models incompatible.
+- 11-05-2023: __v1.9.0__ released! 🔥 Important whisper updates ( https://github.com/go-skynet/LocalAI/pull/233 https://github.com/go-skynet/LocalAI/pull/229 ) and extended gpt4all model families support ( https://github.com/go-skynet/LocalAI/pull/232 ). Redpajama/dolly experimental ( https://github.com/go-skynet/LocalAI/pull/214 )
+- 10-05-2023: __v1.8.0__ released! 🔥 Added support for fast and accurate embeddings with `bert.cpp` ( https://github.com/go-skynet/LocalAI/pull/222 )
 - 09-05-2023: Added experimental support for transcriptions endpoint ( https://github.com/go-skynet/LocalAI/pull/211 )
 - 08-05-2023: Support for embeddings with models using the `llama.cpp` backend ( https://github.com/go-skynet/LocalAI/pull/207 )
 - 02-05-2023: Support for `rwkv.cpp` models ( https://github.com/go-skynet/LocalAI/pull/158 ) and for `/edits` endpoint
@@ -36,7 +56,8 @@ Twitter: [@LocalAI_API](https://twitter.com/LocalAI_API) and [@mudler_it](https:

 ### Blogs and articles

- [Tutorial to use k8sgpt with LocalAI](https://medium.com/@tyler_97636/k8sgpt-localai-unlock-kubernetes-superpowers-for-free-584790de9b65) - excellent usecase for localAI, using AI to analyse Kubernetes clusters.
+- [Question Answering on Documents locally with LangChain, LocalAI, Chroma, and GPT4All](https://mudler.pm/posts/localai-question-answering/) by Ettore Di Giacinto
+- [Tutorial to use k8sgpt with LocalAI](https://medium.com/@tyler_97636/k8sgpt-localai-unlock-kubernetes-superpowers-for-free-584790de9b65) - excellent usecase for localAI, using AI to analyse Kubernetes clusters. by Tyller Gillson

 ## Contribute and help

@@ -57,16 +78,14 @@ It is compatible with the models supported by [llama.cpp](https://github.com/gge
 Tested with:
 - Vicuna
 - Alpaca
- [GPT4ALL](https://github.com/nomic-ai/gpt4all) (changes required, see below)
+- [GPT4ALL](https://gpt4all.io)
 - [GPT4ALL-J](https://gpt4all.io/models/ggml-gpt4all-j.bin) (no changes required)
 - Koala
 - [cerebras-GPT with ggml](https://huggingface.co/lxe/Cerebras-GPT-2.7B-Alpaca-SP-ggml)
 - WizardLM
 - [RWKV](https://github.com/BlinkDL/RWKV-LM) models with [rwkv.cpp](https://github.com/saharNooby/rwkv.cpp)

-### GPT4ALL
-
-Note: You might need to convert older models to the new format, see [here](https://github.com/ggerganov/llama.cpp#using-gpt4all) for instance to run `gpt4all`.
+Note: You might need to convert some models from older models to the new format, for indications, see [the README in llama.cpp](https://github.com/ggerganov/llama.cpp#using-gpt4all) for instance to run `gpt4all`.

 ### RWKV

@@ -92,11 +111,11 @@ It should also be compatible with StableLM and GPTNeoX ggml models (untested).
 Depending on the model you are attempting to run might need more RAM or CPU resources. Check out also [here](https://github.com/ggerganov/llama.cpp#memorydisk-requirements) for `ggml` based backends. `rwkv` is less expensive on resources.


-### Feature support matrix
+### Model compatibility table

 <details>

-| Backend         | Compatible models     | Completion/Chat endpoint | Audio transcription | Embeddings support                | Token stream support | Github                                     | Bindings                                  |
+| Backend         | Compatible models     | Completion/Chat endpoint | Audio transcription/Image | Embeddings support                | Token stream support | Github                                     | Bindings                                  |
 |-----------------|-----------------------|--------------------------|---------------------|-----------------------------------|----------------------|--------------------------------------------|-------------------------------------------|
 | llama           | Vicuna, Alpaca, LLaMa | yes                      | no                  | yes (doesn't seem to be accurate) | yes                  | https://github.com/ggerganov/llama.cpp     | https://github.com/go-skynet/go-llama.cpp |
 | gpt4all-llama   | Vicuna, Alpaca, LLaMa | yes                      | no                  | no                                | yes                  | https://github.com/nomic-ai/gpt4all        | https://github.com/go-skynet/gpt4all      |
@@ -106,12 +125,14 @@ Depending on the model you are attempting to run might need more RAM or CPU reso
 | dolly           | Dolly                 | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
 | redpajama       | RedPajama             | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
 | stableLM        | StableLM GPT/NeoX     | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
+| replit       | Replit             | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
+| gptneox       | GPT NeoX             | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
 | starcoder       | Starcoder             | yes                      | no                  | no                                | no                   | https://github.com/ggerganov/ggml          | https://github.com/go-skynet/go-gpt2.cpp  |
 | bloomz          | Bloom                 | yes                      | no                  | no                                | no                   | https://github.com/NouamaneTazi/bloomz.cpp | https://github.com/go-skynet/bloomz.cpp   |
 | rwkv            | RWKV                  | yes                      | no                  | no                                | yes                  | https://github.com/saharNooby/rwkv.cpp     | https://github.com/donomii/go-rwkv.cpp    |
 | bert-embeddings | bert                  | no                       | no                  | yes                               | no                   | https://github.com/skeskinen/bert.cpp      | https://github.com/go-skynet/go-bert.cpp  |
-| whisper         | whisper               | no                       | yes                 | no                                | no                   | https://github.com/ggerganov/whisper.cpp   | https://github.com/ggerganov/whisper.cpp  |
-
+| whisper         | whisper               | no                       | Audio                 | no                                | no                   | https://github.com/ggerganov/whisper.cpp   | https://github.com/ggerganov/whisper.cpp  |
+| stablediffusion         | stablediffusion               | no                       | Image                 | no                                | no                   | https://github.com/EdVince/Stable-Diffusion-NCNN   | https://github.com/mudler/go-stable-diffusion  |
 </details>

 ## Usage
@@ -136,7 +157,9 @@ cp your-model.bin models/
 # vim .env

 # start with docker-compose
-docker-compose up -d --build
+docker-compose up -d --pull always
+# or you can build the images with:
+# docker-compose up -d --build

 # Now API is accessible at localhost:8080
 curl http://localhost:8080/v1/models
@@ -172,8 +195,9 @@ cp -rf prompt-templates/ggml-gpt4all-j.tmpl models/
 # vim .env

 # start with docker-compose
-docker-compose up -d --build
-
+docker-compose up -d --pull always
+# or you can build the images with:
+# docker-compose up -d --build
 # Now API is accessible at localhost:8080
 curl http://localhost:8080/v1/models
 # {"object":"list","data":[{"id":"ggml-gpt4all-j","object":"model"}]}
@@ -192,6 +216,8 @@ 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 for question answering or for using it with chatbot-ui, see: [examples](https://github.com/go-skynet/LocalAI/tree/master/examples/).


@@ -282,6 +308,73 @@ Specifying a `config-file` via CLI allows to declare models in a single file as

 See also [chatbot-ui](https://github.com/go-skynet/LocalAI/tree/master/examples/chatbot-ui) as an example on how to use config files.

+### Full config model file reference
+
+```yaml
+name: gpt-3.5-turbo
+
+# Default model parameters
+parameters:
+  # Relative to the models path
+  model: ggml-gpt4all-j
+  # temperature
+  temperature: 0.3
+  # all the OpenAI request options here..
+  top_k: 
+  top_p: 
+  max_tokens:
+  batch:
+  f16: true
+  ignore_eos: true
+  n_keep: 10
+  seed: 
+  mode: 
+  step: 
+
+# Default context size
+context_size: 512
+# Default number of threads
+threads: 10
+# Define a backend (optional). By default it will try to guess the backend the first time the model is interacted with.
+backend: gptj # available: llama, stablelm, gpt2, gptj rwkv
+# stopwords (if supported by the backend)
+stopwords:
+- "HUMAN:"
+- "### Response:"
+# string to trim space to
+trimspace:
+- string
+# Strings to cut from the response
+cutstrings:
+- "string"
+# define chat roles
+roles:
+  user: "HUMAN:"
+  system: "GPT:"
+  assistant: "ASSISTANT:"
+template:
+  # template file ".tmpl" with the prompt template to use by default on the endpoint call. Note there is no extension in the files
+  completion: completion
+  chat: ggml-gpt4all-j
+  edit: edit_template
+
+# Enable F16 if backend supports it
+f16: true
+# Enable debugging
+debug: true
+# Enable embeddings
+embeddings: true
+# Mirostat configuration (llama.cpp only)
+mirostat_eta: 0.8
+mirostat_tau: 0.9
+mirostat: 1
+
+# GPU Layers (only used when built with cublas)
+gpu_layers: 22
+
+# Directory used to store additional assets (used for stablediffusion)
+asset_dir: ""
+```
 </details>

 ### Prompt templates 
@@ -339,6 +432,8 @@ local-ai --models-path <model_path> [--address <address>] [--threads <num_thread
 | context-size | CONTEXT_SIZE         | 512           | Default token context size. |
 | debug | DEBUG         | false           | Enable debug mode. |
 | config-file | CONFIG_FILE         | empty           | Path to a LocalAI config file. |
+| upload_limit | UPLOAD_LIMIT         | 5MB           | Upload limit for whisper. |
+| image-dir | CONFIG_FILE         | empty           | Image directory to store and serve processed images. |

 </details>

@@ -431,6 +526,48 @@ curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/jso

 </details>

+### Build with Image generation support
+
+<details>
+
+**Requirements**: OpenCV, Gomp
+
+Image generation is experimental and requires `GO_TAGS=stablediffusion` to be set during build:
+
+```
+make GO_TAGS=stablediffusion rebuild
+```
+
+</details>
+
+### Accelleration
+
+#### OpenBLAS
+
+<details>
+
+Requirements: OpenBLAS
+
+```
+make BUILD_TYPE=openblas build
+```
+
+</details>
+
+#### CuBLAS
+
+<details>
+
+Requirement: Nvidia CUDA toolkit
+
+Note: CuBLAS support is experimental, and has not been tested on real HW. please report any issues you find!
+
+```
+make BUILD_TYPE=cublas build
+```
+
+</details>
+
 ### Windows compatibility

 It should work, however you need to make sure you give enough resources to the container. See https://github.com/go-skynet/LocalAI/issues/2
@@ -559,6 +696,8 @@ curl http://localhost:8080/v1/models

 ### Embeddings

+OpenAI docs: https://platform.openai.com/docs/api-reference/embeddings
+
 <details>

 The embedding endpoint is experimental and enabled only if the model is configured with `embeddings: true` in its `yaml` file, for example:
@@ -601,6 +740,81 @@ curl http://localhost:8080/v1/audio/transcriptions -H "Content-Type: multipart/f
 {"text":"My fellow Americans, this day has brought terrible news and great sadness to our country.At nine o'clock this morning, Mission Control in Houston lost contact with our Space ShuttleColumbia.A short time later, debris was seen falling from the skies above Texas.The Columbia's lost.There are no survivors.One board was a crew of seven.Colonel Rick Husband, Lieutenant Colonel Michael Anderson, Commander Laurel Clark, Captain DavidBrown, Commander William McCool, Dr. Kultna Shavla, and Elon Ramon, a colonel in the IsraeliAir Force.These men and women assumed great risk in the service to all humanity.In an age when spaceflight has come to seem almost routine, it is easy to overlook thedangers of travel by rocket and the difficulties of navigating the fierce outer atmosphere ofthe Earth.These astronauts knew the dangers, and they faced them willingly, knowing they had a highand noble purpose in life.Because of their courage and daring and idealism, we will miss them all the more.All Americans today are thinking as well of the families of these men and women who havebeen given this sudden shock and grief.You're not alone.Our entire nation agrees with you, and those you loved will always have the respect andgratitude of this country.The cause in which they died will continue.Mankind has led into the darkness beyond our world by the inspiration of discovery andthe longing to understand.Our journey into space will go on.In the skies today, we saw destruction and tragedy.As farther than we can see, there is comfort and hope.In the words of the prophet Isaiah, \"Lift your eyes and look to the heavens who createdall these, he who brings out the starry hosts one by one and calls them each by name.\"Because of his great power and mighty strength, not one of them is missing.The same creator who names the stars also knows the names of the seven souls we mourntoday.The crew of the shuttle Columbia did not return safely to Earth yet we can pray that all aresafely home.May God bless the grieving families and may God continue to bless America.[BLANK_AUDIO]"}
 ```

+</details>
+  
+### Image generation
+
+OpenAI docs: https://platform.openai.com/docs/api-reference/images/create
+
+LocalAI supports generating images with Stable diffusion, running on CPU.
+
+| mode=0                                                                                                                | mode=1 (winograd/sgemm)                                                                                                                |
+|------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------|
+| ![test](https://github.com/go-skynet/LocalAI/assets/2420543/7145bdee-4134-45bb-84d4-f11cb08a5638)                      | ![b643343452981](https://github.com/go-skynet/LocalAI/assets/2420543/abf14de1-4f50-4715-aaa4-411d703a942a)          |
+| ![b6441997879](https://github.com/go-skynet/LocalAI/assets/2420543/d50af51c-51b7-4f39-b6c2-bf04c403894c)              | ![winograd2](https://github.com/go-skynet/LocalAI/assets/2420543/1935a69a-ecce-4afc-a099-1ac28cb649b3)                |
+| ![winograd](https://github.com/go-skynet/LocalAI/assets/2420543/1979a8c4-a70d-4602-95ed-642f382f6c6a)                | ![winograd3](https://github.com/go-skynet/LocalAI/assets/2420543/e6d184d4-5002-408f-b564-163986e1bdfb)                |
+
+<details>
+
+To generate an image you can send a POST request to the `/v1/images/generations` endpoint with the instruction as the request body:
+
+```bash
+# 512x512 is supported too
+curl http://localhost:8080/v1/images/generations -H "Content-Type: application/json" -d '{
+            "prompt": "A cute baby sea otter",
+            "size": "256x256" 
+          }'
+```
+
+Available additional parameters: `mode`, `step`.
+
+Note: To set a negative prompt, you can split the prompt with `|`, for instance: `a cute baby sea otter|malformed`.
+
+```bash
+curl http://localhost:8080/v1/images/generations -H "Content-Type: application/json" -d '{
+            "prompt": "floating hair, portrait, ((loli)), ((one girl)), cute face, hidden hands, asymmetrical bangs, beautiful detailed eyes, eye shadow, hair ornament, ribbons, bowties, buttons, pleated skirt, (((masterpiece))), ((best quality)), colorful|((part of the head)), ((((mutated hands and fingers)))), deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, Octane renderer, lowres, bad anatomy, bad hands, text",
+            "size": "256x256"
+          }'
+```
+
+Note: image generator supports images up to 512x512. You can use other tools however to upscale the image, for instance: https://github.com/upscayl/upscayl.
+
+#### Setup
+
+Note: In order to use the `images/generation` endpoint, you need to build LocalAI with `GO_TAGS=stablediffusion`.
+
+1. Create a model file `stablediffusion.yaml` in the models folder:
+
+```yaml
+name: stablediffusion
+backend: stablediffusion
+asset_dir: stablediffusion_assets
+```
+2. Create a `stablediffusion_assets` directory inside your `models` directory
+3. Download the ncnn assets from https://github.com/EdVince/Stable-Diffusion-NCNN#out-of-box and place them in `stablediffusion_assets`.
+
+The models directory should look like the following:
+
+```
+models
+├── stablediffusion_assets
+│   ├── AutoencoderKL-256-256-fp16-opt.param
+│   ├── AutoencoderKL-512-512-fp16-opt.param
+│   ├── AutoencoderKL-base-fp16.param
+│   ├── AutoencoderKL-encoder-512-512-fp16.bin
+│   ├── AutoencoderKL-fp16.bin
+│   ├── FrozenCLIPEmbedder-fp16.bin
+│   ├── FrozenCLIPEmbedder-fp16.param
+│   ├── log_sigmas.bin
+│   ├── tmp-AutoencoderKL-encoder-256-256-fp16.param
+│   ├── UNetModel-256-256-MHA-fp16-opt.param
+│   ├── UNetModel-512-512-MHA-fp16-opt.param
+│   ├── UNetModel-base-MHA-fp16.param
+│   ├── UNetModel-MHA-fp16.bin
+│   └── vocab.txt
+└── stablediffusion.yaml
+```
+
 </details>

 ## Frequently asked questions
@@ -639,7 +853,7 @@ Yes! If the client uses OpenAI and supports setting a different base URL to send

 <details>

-Not currently, as ggml doesn't support GPUs yet: https://github.com/ggerganov/llama.cpp/discussions/915.
+There is partial GPU support, see build instructions above.

 </details>

@@ -679,6 +893,9 @@ Feel free to open up a PR to get your project listed!
 - [x] Multi-model support
 - [x] Have a webUI!
 - [x] Allow configuration of defaults for models.
+- [x] Support for embeddings
+- [x] Support for audio transcription with https://github.com/ggerganov/whisper.cpp
+- [ ] GPU/CUDA support ( https://github.com/go-skynet/LocalAI/issues/69 )
 - [ ] Enable automatic downloading of models from a curated gallery, with only free-licensed models, directly from the webui.

 ## Star history
@@ -701,10 +918,15 @@ MIT

 ## Acknowledgements

+LocalAI couldn't have been built without the help of great software already available from the community. Thank you!
+
 - [llama.cpp](https://github.com/ggerganov/llama.cpp)
 - https://github.com/tatsu-lab/stanford_alpaca
 - https://github.com/cornelk/llama-go for the initial ideas
- https://github.com/antimatter15/alpaca.cpp for the light model version (this is compatible and tested only with that checkpoint model!)
+- https://github.com/antimatter15/alpaca.cpp
+- https://github.com/EdVince/Stable-Diffusion-NCNN
+- https://github.com/ggerganov/whisper.cpp
+- https://github.com/saharNooby/rwkv.cpp

 ## Contributors

--- a/api/api.go
+++ b/api/api.go
@@ -12,7 +12,7 @@ import (
 	"github.com/rs/zerolog/log"
 )

-func App(configFile string, loader *model.ModelLoader, threads, ctxSize int, f16 bool, debug, disableMessage bool) *fiber.App {
+func App(configFile string, loader *model.ModelLoader, uploadLimitMB, threads, ctxSize int, f16 bool, debug, disableMessage bool, imageDir string) *fiber.App {
 	zerolog.SetGlobalLevel(zerolog.InfoLevel)
 	if debug {
 		zerolog.SetGlobalLevel(zerolog.DebugLevel)
@@ -20,6 +20,7 @@ func App(configFile string, loader *model.ModelLoader, threads, ctxSize int, f16

 	// Return errors as JSON responses
 	app := fiber.New(fiber.Config{
+		BodyLimit:             uploadLimitMB * 1024 * 1024, // this is the default limit of 4MB
 		DisableStartupMessage: disableMessage,
 		// Override default error handler
 		ErrorHandler: func(ctx *fiber.Ctx, err error) error {
@@ -86,6 +87,12 @@ func App(configFile string, loader *model.ModelLoader, threads, ctxSize int, f16

 	app.Post("/v1/audio/transcriptions", transcriptEndpoint(cm, debug, loader, threads, ctxSize, f16))

+	app.Post("/v1/images/generations", imageEndpoint(cm, debug, loader, imageDir))
+
+	if imageDir != "" {
+		app.Static("/generated-images", imageDir)
+	}
+
 	app.Get("/v1/models", listModels(loader, cm))
 	app.Get("/models", listModels(loader, cm))

--- a/api/api_test.go
+++ b/api/api_test.go
@@ -3,6 +3,8 @@ package api_test
 import (
 	"context"
 	"os"
+	"path/filepath"
+	"runtime"

 	. "github.com/go-skynet/LocalAI/api"
 	"github.com/go-skynet/LocalAI/pkg/model"
@@ -23,7 +25,7 @@ var _ = Describe("API test", func() {
 	Context("API query", func() {
 		BeforeEach(func() {
 			modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
-			app = App("", modelLoader, 1, 512, false, true, true)
+			app = App("", modelLoader, 15, 1, 512, false, true, true, "")
 			go app.Listen("127.0.0.1:9090")

 			defaultConfig := openai.DefaultConfig("")
@@ -45,8 +47,7 @@ var _ = Describe("API test", func() {
 		It("returns the models list", func() {
 			models, err := client.ListModels(context.TODO())
 			Expect(err).ToNot(HaveOccurred())
-			Expect(len(models.Models)).To(Equal(3))
-			Expect(models.Models[0].ID).To(Equal("testmodel"))
+			Expect(len(models.Models)).To(Equal(10))
 		})
 		It("can generate completions", func() {
 			resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "testmodel", Prompt: "abcdedfghikl"})
@@ -79,15 +80,67 @@ var _ = Describe("API test", func() {
 		It("returns errors", func() {
 			_, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "foomodel", Prompt: "abcdedfghikl"})
 			Expect(err).To(HaveOccurred())
-			Expect(err.Error()).To(ContainSubstring("error, status code: 500, message: could not load model - all backends returned error: 10 errors occurred:"))
+			Expect(err.Error()).To(ContainSubstring("error, status code: 500, message: could not load model - all backends returned error: 12 errors occurred:"))
+		})
+		It("transcribes audio", func() {
+			if runtime.GOOS != "linux" {
+				Skip("test supported only on linux")
+			}
+			resp, err := client.CreateTranscription(
+				context.Background(),
+				openai.AudioRequest{
+					Model:    openai.Whisper1,
+					FilePath: filepath.Join(os.Getenv("TEST_DIR"), "audio.wav"),
+				},
+			)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(resp.Text).To(ContainSubstring("This is the Micro Machine Man presenting"))
 		})

+		It("calculate embeddings", func() {
+			if runtime.GOOS != "linux" {
+				Skip("test supported only on linux")
+			}
+			resp, err := client.CreateEmbeddings(
+				context.Background(),
+				openai.EmbeddingRequest{
+					Model: openai.AdaEmbeddingV2,
+					Input: []string{"sun", "cat"},
+				},
+			)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 384))
+			Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 384))
+
+			sunEmbedding := resp.Data[0].Embedding
+			resp2, err := client.CreateEmbeddings(
+				context.Background(),
+				openai.EmbeddingRequest{
+					Model: openai.AdaEmbeddingV2,
+					Input: []string{"sun"},
+				},
+			)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(resp2.Data[0].Embedding).To(Equal(sunEmbedding))
+		})
+
+		Context("backends", func() {
+			It("runs rwkv", func() {
+				if runtime.GOOS != "linux" {
+					Skip("test supported only on linux")
+				}
+				resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "rwkv_test", Prompt: "Count up to five: one, two, three, four,"})
+				Expect(err).ToNot(HaveOccurred())
+				Expect(len(resp.Choices) > 0).To(BeTrue())
+				Expect(resp.Choices[0].Text).To(Equal(" five."))
+			})
+		})
 	})

 	Context("Config file", func() {
 		BeforeEach(func() {
 			modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
-			app = App(os.Getenv("CONFIG_FILE"), modelLoader, 1, 512, false, true, true)
+			app = App(os.Getenv("CONFIG_FILE"), modelLoader, 5, 1, 512, false, true, true, "")
 			go app.Listen("127.0.0.1:9090")

 			defaultConfig := openai.DefaultConfig("")
@@ -108,8 +161,7 @@ var _ = Describe("API test", func() {

 			models, err := client.ListModels(context.TODO())
 			Expect(err).ToNot(HaveOccurred())
-			Expect(len(models.Models)).To(Equal(5))
-			Expect(models.Models[0].ID).To(Equal("testmodel"))
+			Expect(len(models.Models)).To(Equal(12))
 		})
 		It("can generate chat completions from config file", func() {
 			resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list1", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "abcdedfghikl"}}})
@@ -134,5 +186,6 @@ var _ = Describe("API test", func() {
 			Expect(len(resp.Choices)).To(Equal(1))
 			Expect(resp.Choices[0].Text).ToNot(BeEmpty())
 		})
+
 	})
 })
--- a/api/config.go
+++ b/api/config.go
@@ -15,23 +15,24 @@ import (
 )

 type Config struct {
-	OpenAIRequest  `yaml:"parameters"`
-	Name           string            `yaml:"name"`
-	StopWords      []string          `yaml:"stopwords"`
-	Cutstrings     []string          `yaml:"cutstrings"`
-	TrimSpace      []string          `yaml:"trimspace"`
-	ContextSize    int               `yaml:"context_size"`
-	F16            bool              `yaml:"f16"`
-	Threads        int               `yaml:"threads"`
-	Debug          bool              `yaml:"debug"`
-	Roles          map[string]string `yaml:"roles"`
-	Embeddings     bool              `yaml:"embeddings"`
-	Backend        string            `yaml:"backend"`
-	TemplateConfig TemplateConfig    `yaml:"template"`
-	MirostatETA    float64           `yaml:"mirostat_eta"`
-	MirostatTAU    float64           `yaml:"mirostat_tau"`
-	Mirostat       int               `yaml:"mirostat"`
-
+	OpenAIRequest               `yaml:"parameters"`
+	Name                        string            `yaml:"name"`
+	StopWords                   []string          `yaml:"stopwords"`
+	Cutstrings                  []string          `yaml:"cutstrings"`
+	TrimSpace                   []string          `yaml:"trimspace"`
+	ContextSize                 int               `yaml:"context_size"`
+	F16                         bool              `yaml:"f16"`
+	Threads                     int               `yaml:"threads"`
+	Debug                       bool              `yaml:"debug"`
+	Roles                       map[string]string `yaml:"roles"`
+	Embeddings                  bool              `yaml:"embeddings"`
+	Backend                     string            `yaml:"backend"`
+	TemplateConfig              TemplateConfig    `yaml:"template"`
+	MirostatETA                 float64           `yaml:"mirostat_eta"`
+	MirostatTAU                 float64           `yaml:"mirostat_tau"`
+	Mirostat                    int               `yaml:"mirostat"`
+	NGPULayers                  int               `yaml:"gpu_layers"`
+	ImageGenerationAssets       string            `yaml:"asset_dir"`
 	PromptStrings, InputStrings []string
 	InputToken                  [][]int
 }
@@ -211,12 +212,11 @@ func updateConfig(config *Config, input *OpenAIRequest) {
 		}
 	}
 }
-
-func readConfig(cm ConfigMerger, c *fiber.Ctx, loader *model.ModelLoader, debug bool, threads, ctx int, f16 bool) (*Config, *OpenAIRequest, error) {
+func readInput(c *fiber.Ctx, loader *model.ModelLoader, randomModel bool) (string, *OpenAIRequest, error) {
 	input := new(OpenAIRequest)
 	// Get input data from the request body
 	if err := c.BodyParser(input); err != nil {
-		return nil, nil, err
+		return "", nil, err
 	}

 	modelFile := input.Model
@@ -234,14 +234,14 @@ func readConfig(cm ConfigMerger, c *fiber.Ctx, loader *model.ModelLoader, debug
 	bearerExists := bearer != "" && loader.ExistsInModelPath(bearer)

 	// If no model was specified, take the first available
-	if modelFile == "" && !bearerExists {
+	if modelFile == "" && !bearerExists && randomModel {
 		models, _ := loader.ListModels()
 		if len(models) > 0 {
 			modelFile = models[0]
 			log.Debug().Msgf("No model specified, using: %s", modelFile)
 		} else {
 			log.Debug().Msgf("No model specified, returning error")
-			return nil, nil, fmt.Errorf("no model specified")
+			return "", nil, fmt.Errorf("no model specified")
 		}
 	}

@@ -250,7 +250,10 @@ func readConfig(cm ConfigMerger, c *fiber.Ctx, loader *model.ModelLoader, debug
 		log.Debug().Msgf("Using model from bearer token: %s", bearer)
 		modelFile = bearer
 	}
+	return modelFile, input, nil
+}

+func readConfig(modelFile string, input *OpenAIRequest, cm ConfigMerger, loader *model.ModelLoader, debug bool, threads, ctx int, f16 bool) (*Config, *OpenAIRequest, error) {
 	// Load a config file if present after the model name
 	modelConfig := filepath.Join(loader.ModelPath, modelFile+".yaml")
 	if _, err := os.Stat(modelConfig); err == nil {
--- a/api/openai.go
+++ b/api/openai.go
@@ -3,13 +3,16 @@ package api
 import (
 	"bufio"
 	"bytes"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
 	"io"
+	"io/ioutil"
 	"net/http"
 	"os"
 	"path"
 	"path/filepath"
+	"strconv"
 	"strings"

 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
@@ -43,6 +46,10 @@ type Item struct {
 	Embedding []float32 `json:"embedding"`
 	Index     int       `json:"index"`
 	Object    string    `json:"object,omitempty"`
+
+	// Images
+	URL     string `json:"url,omitempty"`
+	B64JSON string `json:"b64_json,omitempty"`
 }

 type OpenAIResponse struct {
@@ -78,11 +85,13 @@ type OpenAIRequest struct {
 	Model string `json:"model" yaml:"model"`

 	// whisper
-	File           string `json:"file" validate:"required"`
+	File     string `json:"file" validate:"required"`
+	Language string `json:"language"`
+	//whisper/image
 	ResponseFormat string `json:"response_format"`
-	Language       string `json:"language"`
-
-	// Prompt is read only by completion API calls
+	// image
+	Size string `json:"size"`
+	// Prompt is read only by completion/image API calls
 	Prompt interface{} `json:"prompt" yaml:"prompt"`

 	// Edit endpoint
@@ -116,6 +125,10 @@ type OpenAIRequest struct {
 	Mirostat    int     `json:"mirostat" yaml:"mirostat"`

 	Seed int `json:"seed" yaml:"seed"`
+
+	// Image (not supported by OpenAI)
+	Mode int `json:"mode"`
+	Step int `json:"step"`
 }

 func defaultRequest(modelFile string) OpenAIRequest {
@@ -131,7 +144,13 @@ func defaultRequest(modelFile string) OpenAIRequest {
 // https://platform.openai.com/docs/api-reference/completions
 func completionEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
+
+		model, input, err := readInput(c, loader, true)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		config, input, err := readConfig(model, input, cm, loader, debug, threads, ctx, f16)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
@@ -182,7 +201,12 @@ func completionEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader,
 // https://platform.openai.com/docs/api-reference/embeddings
 func embeddingsEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
+		model, input, err := readInput(c, loader, true)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		config, input, err := readConfig(model, input, cm, loader, debug, threads, ctx, f16)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
@@ -249,7 +273,12 @@ func chatEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, thread
 		close(responses)
 	}
 	return func(c *fiber.Ctx) error {
-		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
+		model, input, err := readInput(c, loader, true)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		config, input, err := readConfig(model, input, cm, loader, debug, threads, ctx, f16)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
@@ -260,12 +289,14 @@ func chatEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, thread

 		mess := []string{}
 		for _, i := range input.Messages {
+			var content string
 			r := config.Roles[i.Role]
-			if r == "" {
-				r = i.Role
+			if r != "" {
+				content = fmt.Sprint(r, " ", i.Content)
+			} else {
+				content = i.Content
 			}

-			content := fmt.Sprint(r, " ", i.Content)
 			mess = append(mess, content)
 		}

@@ -349,7 +380,12 @@ func chatEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, thread

 func editEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
+		model, input, err := readInput(c, loader, true)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		config, input, err := readConfig(model, input, cm, loader, debug, threads, ctx, f16)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
@@ -398,25 +434,167 @@ func editEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, thread
 	}
 }

-// https://platform.openai.com/docs/api-reference/audio/create
-func transcriptEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
+// https://platform.openai.com/docs/api-reference/images/create
+
+/*
+*
+
+	curl http://localhost:8080/v1/images/generations \
+	  -H "Content-Type: application/json" \
+	  -d '{
+	    "prompt": "A cute baby sea otter",
+	    "n": 1,
+	    "size": "512x512"
+	  }'
+
+*
+*/
+func imageEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, imageDir string) func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		config, input, err := readConfig(cm, c, loader, debug, threads, ctx, f16)
+		m, input, err := readInput(c, loader, false)
 		if err != nil {
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}

+		if m == "" {
+			m = model.StableDiffusionBackend
+		}
+		log.Debug().Msgf("Loading model: %+v", m)
+
+		config, input, err := readConfig(m, input, cm, loader, debug, 0, 0, false)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		log.Debug().Msgf("Parameter Config: %+v", config)
+
+		// XXX: Only stablediffusion is supported for now
+		if config.Backend == "" {
+			config.Backend = model.StableDiffusionBackend
+		}
+
+		sizeParts := strings.Split(input.Size, "x")
+		if len(sizeParts) != 2 {
+			return fmt.Errorf("Invalid value for 'size'")
+		}
+		width, err := strconv.Atoi(sizeParts[0])
+		if err != nil {
+			return fmt.Errorf("Invalid value for 'size'")
+		}
+		height, err := strconv.Atoi(sizeParts[1])
+		if err != nil {
+			return fmt.Errorf("Invalid value for 'size'")
+		}
+
+		b64JSON := false
+		if input.ResponseFormat == "b64_json" {
+			b64JSON = true
+		}
+
+		var result []Item
+		for _, i := range config.PromptStrings {
+			n := input.N
+			if input.N == 0 {
+				n = 1
+			}
+			for j := 0; j < n; j++ {
+				prompts := strings.Split(i, "|")
+				positive_prompt := prompts[0]
+				negative_prompt := ""
+				if len(prompts) > 1 {
+					negative_prompt = prompts[1]
+				}
+
+				mode := 0
+				step := 15
+
+				if input.Mode != 0 {
+					mode = input.Mode
+				}
+
+				if input.Step != 0 {
+					step = input.Step
+				}
+
+				tempDir := ""
+				if !b64JSON {
+					tempDir = imageDir
+				}
+				// Create a temporary file
+				outputFile, err := ioutil.TempFile(tempDir, "b64")
+				if err != nil {
+					return err
+				}
+				outputFile.Close()
+				output := outputFile.Name() + ".png"
+				// Rename the temporary file
+				err = os.Rename(outputFile.Name(), output)
+				if err != nil {
+					return err
+				}
+
+				baseURL := c.BaseURL()
+
+				fn, err := ImageGeneration(height, width, mode, step, input.Seed, positive_prompt, negative_prompt, output, loader, *config)
+				if err != nil {
+					return err
+				}
+				if err := fn(); err != nil {
+					return err
+				}
+
+				item := &Item{}
+
+				if b64JSON {
+					defer os.RemoveAll(output)
+					data, err := os.ReadFile(output)
+					if err != nil {
+						return err
+					}
+					item.B64JSON = base64.StdEncoding.EncodeToString(data)
+				} else {
+					base := filepath.Base(output)
+					item.URL = baseURL + "/generated-images/" + base
+				}
+
+				result = append(result, *item)
+			}
+		}
+
+		resp := &OpenAIResponse{
+			Data: result,
+		}
+
+		jsonResult, _ := json.Marshal(resp)
+		log.Debug().Msgf("Response: %s", jsonResult)
+
+		// Return the prediction in the response body
+		return c.JSON(resp)
+	}
+}
+
+// https://platform.openai.com/docs/api-reference/audio/create
+func transcriptEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader, threads, ctx int, f16 bool) func(c *fiber.Ctx) error {
+	return func(c *fiber.Ctx) error {
+		m, input, err := readInput(c, loader, false)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
+
+		config, input, err := readConfig(m, input, cm, loader, debug, threads, ctx, f16)
+		if err != nil {
+			return fmt.Errorf("failed reading parameters from request:%w", err)
+		}
 		// retrieve the file data from the request
 		file, err := c.FormFile("file")
 		if err != nil {
-			return c.Status(http.StatusBadRequest).JSON(fiber.Map{"error": err.Error()})
+			return err
 		}
 		f, err := file.Open()
 		if err != nil {
-			return c.Status(http.StatusBadRequest).JSON(fiber.Map{"error": err.Error()})
+			return err
 		}
 		defer f.Close()
-		log.Debug().Msgf("Audio file: %+v", file)

 		dir, err := os.MkdirTemp("", "whisper")

@@ -428,26 +606,33 @@ func transcriptEndpoint(cm ConfigMerger, debug bool, loader *model.ModelLoader,
 		dst := filepath.Join(dir, path.Base(file.Filename))
 		dstFile, err := os.Create(dst)
 		if err != nil {
-			return c.Status(http.StatusBadRequest).JSON(fiber.Map{"error": err.Error()})
+			return err
 		}

 		if _, err := io.Copy(dstFile, f); err != nil {
-			log.Debug().Msgf("Audio file %+v - %+v - err %+v", file.Filename, dst, err)
+			log.Debug().Msgf("Audio file copying error %+v - %+v - err %+v", file.Filename, dst, err)
 			return err
 		}

 		log.Debug().Msgf("Audio file copied to: %+v", dst)

-		whisperModel, err := loader.BackendLoader("whisper", config.Model, []llama.ModelOption{}, uint32(config.Threads))
+		whisperModel, err := loader.BackendLoader(model.WhisperBackend, config.Model, []llama.ModelOption{}, uint32(config.Threads))
 		if err != nil {
-			return c.Status(http.StatusBadRequest).JSON(fiber.Map{"error": err.Error()})
+			return err
 		}

-		w := whisperModel.(whisper.Model)
+		if whisperModel == nil {
+			return fmt.Errorf("could not load whisper model")
+		}

-		tr, err := whisperutil.Transcript(w, dst, input.Language)
+		w, ok := whisperModel.(whisper.Model)
+		if !ok {
+			return fmt.Errorf("loader returned non-whisper object")
+		}
+
+		tr, err := whisperutil.Transcript(w, dst, input.Language, uint(config.Threads))
 		if err != nil {
-			return c.Status(http.StatusBadRequest).JSON(fiber.Map{"error": err.Error()})
+			return err
 		}

 		log.Debug().Msgf("Trascribed: %+v", tr)
--- a/api/prediction.go
+++ b/api/prediction.go
@@ -8,11 +8,12 @@ import (

 	"github.com/donomii/go-rwkv.cpp"
 	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/stablediffusion"
 	"github.com/go-skynet/bloomz.cpp"
 	bert "github.com/go-skynet/go-bert.cpp"
 	gpt2 "github.com/go-skynet/go-gpt2.cpp"
 	llama "github.com/go-skynet/go-llama.cpp"
-	gpt4all "github.com/nomic/gpt4all/gpt4all-bindings/golang"
+	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
 )

 // mutex still needed, see: https://github.com/ggerganov/llama.cpp/discussions/784
@@ -31,9 +32,52 @@ func defaultLLamaOpts(c Config) []llama.ModelOption {
 		llamaOpts = append(llamaOpts, llama.EnableEmbeddings)
 	}

+	if c.NGPULayers != 0 {
+		llamaOpts = append(llamaOpts, llama.SetGPULayers(c.NGPULayers))
+	}
+
 	return llamaOpts
 }

+func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, dst string, loader *model.ModelLoader, c Config) (func() error, error) {
+	if c.Backend != model.StableDiffusionBackend {
+		return nil, fmt.Errorf("endpoint only working with stablediffusion models")
+	}
+	inferenceModel, err := loader.BackendLoader(c.Backend, c.ImageGenerationAssets, []llama.ModelOption{}, uint32(c.Threads))
+	if err != nil {
+		return nil, err
+	}
+
+	var fn func() error
+	switch model := inferenceModel.(type) {
+	case *stablediffusion.StableDiffusion:
+		fn = func() error {
+			return model.GenerateImage(height, width, mode, step, seed, positive_prompt, negative_prompt, dst)
+		}
+
+	default:
+		fn = func() error {
+			return fmt.Errorf("creation of images not supported by the backend")
+		}
+	}
+
+	return func() error {
+		// This is still needed, see: https://github.com/ggerganov/llama.cpp/discussions/784
+		mutexMap.Lock()
+		l, ok := mutexes[c.Backend]
+		if !ok {
+			m := &sync.Mutex{}
+			mutexes[c.Backend] = m
+			l = m
+		}
+		mutexMap.Unlock()
+		l.Lock()
+		defer l.Unlock()
+
+		return fn()
+	}, nil
+}
+
 func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, c Config) (func() ([]float32, error), error) {
 	if !c.Embeddings {
 		return nil, fmt.Errorf("endpoint disabled for this model by API configuration")
@@ -68,7 +112,7 @@ func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, c Config)
 	case *bert.Bert:
 		fn = func() ([]float32, error) {
 			if len(tokens) > 0 {
-				return nil, fmt.Errorf("embeddings endpoint for this model supports only string")
+				return model.TokenEmbeddings(tokens, bert.SetThreads(c.Threads))
 			}
 			return model.Embeddings(s, bert.SetThreads(c.Threads))
 		}
@@ -199,6 +243,54 @@ func ModelInference(s string, loader *model.ModelLoader, c Config, tokenCallback

 			return response, nil
 		}
+	case *gpt2.GPTNeoX:
+		fn = func() (string, error) {
+			// Generate the prediction using the language model
+			predictOptions := []gpt2.PredictOption{
+				gpt2.SetTemperature(c.Temperature),
+				gpt2.SetTopP(c.TopP),
+				gpt2.SetTopK(c.TopK),
+				gpt2.SetTokens(c.Maxtokens),
+				gpt2.SetThreads(c.Threads),
+			}
+
+			if c.Batch != 0 {
+				predictOptions = append(predictOptions, gpt2.SetBatch(c.Batch))
+			}
+
+			if c.Seed != 0 {
+				predictOptions = append(predictOptions, gpt2.SetSeed(c.Seed))
+			}
+
+			return model.Predict(
+				s,
+				predictOptions...,
+			)
+		}
+	case *gpt2.Replit:
+		fn = func() (string, error) {
+			// Generate the prediction using the language model
+			predictOptions := []gpt2.PredictOption{
+				gpt2.SetTemperature(c.Temperature),
+				gpt2.SetTopP(c.TopP),
+				gpt2.SetTopK(c.TopK),
+				gpt2.SetTokens(c.Maxtokens),
+				gpt2.SetThreads(c.Threads),
+			}
+
+			if c.Batch != 0 {
+				predictOptions = append(predictOptions, gpt2.SetBatch(c.Batch))
+			}
+
+			if c.Seed != 0 {
+				predictOptions = append(predictOptions, gpt2.SetSeed(c.Seed))
+			}
+
+			return model.Predict(
+				s,
+				predictOptions...,
+			)
+		}
 	case *gpt2.Starcoder:
 		fn = func() (string, error) {
 			// Generate the prediction using the language model
--- a/examples/README.md
+++ b/examples/README.md
@@ -65,7 +65,7 @@ Run a slack bot which lets you talk directly with a model

 [Check it out here](https://github.com/go-skynet/LocalAI/tree/master/examples/slack-bot/)

-### Question answering on documents
+### Question answering on documents with llama-index

 _by [@mudler](https://github.com/mudler)_

@@ -73,6 +73,14 @@ Shows how to integrate with [Llama-Index](https://gpt-index.readthedocs.io/en/st

 [Check it out here](https://github.com/go-skynet/LocalAI/tree/master/examples/query_data/)

+### Question answering on documents with langchain and chroma
+
+_by [@mudler](https://github.com/mudler)_
+
+Shows how to integrate with `Langchain` and `Chroma` to enable question answering on a set of documents.
+
+[Check it out here](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain-chroma/)
+
 ### Template for Runpod.io

 _by [@fHachenberg](https://github.com/fHachenberg)_
--- a/examples/chatbot-ui/README.md
+++ b/examples/chatbot-ui/README.md
@@ -19,7 +19,9 @@ cd LocalAI/examples/chatbot-ui
 wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j

 # start with docker-compose
-docker-compose up -d --build
+docker-compose up -d --pull always
+# or you can build the images with:
+# docker-compose up -d --build
 ```

 ## Pointing chatbot-ui to a separately managed LocalAI service
--- a/examples/langchain-chroma/README.md
+++ b/examples/langchain-chroma/README.md
@@ -0,0 +1,54 @@
+# Data query example
+
+This example makes use of [langchain and chroma](https://blog.langchain.dev/langchain-chroma/) to enable question answering on a set of documents.
+
+## Setup
+
+Download the models and start the API:
+
+```bash
+# Clone LocalAI
+git clone https://github.com/go-skynet/LocalAI
+
+cd LocalAI/examples/query_data
+
+wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O models/bert
+wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j
+
+# start with docker-compose
+docker-compose up -d --build
+```
+
+### Python requirements
+
+```
+pip install -r requirements.txt
+```
+
+### Create a storage
+
+In this step we will create a local vector database from our document set, so later we can ask questions on it with the LLM.
+
+```bash
+export OPENAI_API_BASE=http://localhost:8080/v1
+export OPENAI_API_KEY=sk-
+
+wget https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt
+python store.py
+```
+
+After it finishes, a directory "storage" will be created with the vector index database.
+
+## Query
+
+We can now query the dataset. 
+
+```bash
+export OPENAI_API_BASE=http://localhost:8080/v1
+export OPENAI_API_KEY=sk-
+
+python query.py
+# President Trump recently stated during a press conference regarding tax reform legislation that "we're getting rid of all these loopholes." He also mentioned that he wants to simplify the system further through changes such as increasing the standard deduction amount and making other adjustments aimed at reducing taxpayers' overall burden.    
+```
+
+Keep in mind now things are hit or miss!
--- a/examples/langchain-chroma/models/completion.tmpl
+++ b/examples/langchain-chroma/models/completion.tmpl
@@ -0,0 +1 @@
+{{.Input}}
--- a/examples/langchain-chroma/models/embeddings.yaml
+++ b/examples/langchain-chroma/models/embeddings.yaml
@@ -0,0 +1,5 @@
+name: text-embedding-ada-002
+parameters:
+  model: bert
+backend: bert-embeddings
+embeddings: true
--- a/examples/langchain-chroma/models/gpt-3.5-turbo.yaml
+++ b/examples/langchain-chroma/models/gpt-3.5-turbo.yaml
@@ -0,0 +1,16 @@
+name: gpt-3.5-turbo
+parameters:
+  model: ggml-gpt4all-j
+  top_k: 80
+  temperature: 0.2
+  top_p: 0.7
+context_size: 1024
+stopwords:
+- "HUMAN:"
+- "GPT:"
+roles:
+  user: " "
+  system: " "
+template:
+  completion: completion
+  chat: gpt4all
--- a/examples/langchain-chroma/models/gpt4all.tmpl
+++ b/examples/langchain-chroma/models/gpt4all.tmpl
@@ -0,0 +1,4 @@
+The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
+### Prompt:
+{{.Input}}
+### Response:
--- a/examples/langchain-chroma/query.py
+++ b/examples/langchain-chroma/query.py
@@ -0,0 +1,20 @@
+
+import os
+from langchain.vectorstores import Chroma
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.chains import VectorDBQA
+
+base_path = os.environ.get('OPENAI_API_BASE', 'http://localhost:8080/v1')
+
+# Load and process the text
+embedding = OpenAIEmbeddings()
+persist_directory = 'db'
+
+# Now we can load the persisted database from disk, and use it as normal. 
+vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)
+qa = VectorDBQA.from_chain_type(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_base=base_path), chain_type="stuff", vectorstore=vectordb)
+
+query = "What the president said about taxes ?"
+print(qa.run(query))
+
--- a/examples/langchain-chroma/requirements.txt
+++ b/examples/langchain-chroma/requirements.txt
@@ -0,0 +1,4 @@
+langchain==0.0.160
+openai==0.27.6
+chromadb==0.3.21
+llama-index==0.6.2
--- a/examples/langchain-chroma/store.py
+++ b/examples/langchain-chroma/store.py
@@ -0,0 +1,28 @@
+
+import os
+from langchain.vectorstores import Chroma
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter,TokenTextSplitter,CharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.chains import VectorDBQA
+from langchain.document_loaders import TextLoader
+
+base_path = os.environ.get('OPENAI_API_BASE', 'http://localhost:8080/v1')
+
+# Load and process the text
+loader = TextLoader('state_of_the_union.txt')
+documents = loader.load()
+
+text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=70)
+#text_splitter = TokenTextSplitter()
+texts = text_splitter.split_documents(documents)
+
+# Embed and store the texts
+# Supplying a persist_directory will store the embeddings on disk
+persist_directory = 'db'
+
+embedding = OpenAIEmbeddings(model="text-embedding-ada-002")
+vectordb = Chroma.from_documents(documents=texts, embedding=embedding, persist_directory=persist_directory)
+
+vectordb.persist()
+vectordb = None
--- a/go.mod
+++ b/go.mod
@@ -3,17 +3,19 @@ module github.com/go-skynet/LocalAI
 go 1.19

 require (
-	github.com/donomii/go-rwkv.cpp v0.0.0-20230510174014-07166da10cb2
-	github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230509153812-1d17cd5bb37a
+	github.com/donomii/go-rwkv.cpp v0.0.0-20230515123100-6fdd0c338e56
+	github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230515153606-95b02d76b04d
 	github.com/go-audio/wav v1.1.0
-	github.com/go-skynet/bloomz.cpp v0.0.0-20230510195113-ad7e89a0885f
-	github.com/go-skynet/go-bert.cpp v0.0.0-20230510124618-ec771ec71557
-	github.com/go-skynet/go-gpt2.cpp v0.0.0-20230509180201-d49823284cc6
+	github.com/go-skynet/bloomz.cpp v0.0.0-20230510223001-e9366e82abdf
+	github.com/go-skynet/go-bert.cpp v0.0.0-20230516063724-cea1ed76a7f4
+	github.com/go-skynet/go-gpt2.cpp v0.0.0-20230512145559-7bff56f02245
 	github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230422090028-1f7bff57f66c
-	github.com/go-skynet/go-llama.cpp v0.0.0-20230510072905-70593fccbe4b
+	github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84
 	github.com/gofiber/fiber/v2 v2.45.0
 	github.com/hashicorp/go-multierror v1.1.1
-	github.com/onsi/ginkgo/v2 v2.9.4
+	github.com/mudler/go-stable-diffusion v0.0.0-20230516152536-c0748eca3642
+	github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230516143155-79d6243fe1bc
+	github.com/onsi/ginkgo/v2 v2.9.5
 	github.com/onsi/gomega v1.27.6
 	github.com/otiai10/copy v1.11.0
 	github.com/otiai10/openaigo v1.1.0
@@ -49,7 +51,6 @@ require (
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.18 // indirect
 	github.com/mattn/go-runewidth v0.0.14 // indirect
-	github.com/nomic/gpt4all/gpt4all-bindings/golang v0.0.0-00010101000000-000000000000 // indirect
 	github.com/philhofer/fwd v1.1.2 // indirect
 	github.com/rivo/uniseg v0.2.0 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
@@ -59,9 +60,9 @@ require (
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/valyala/tcplisten v1.0.0 // indirect
 	github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 // indirect
-	golang.org/x/net v0.9.0 // indirect
+	golang.org/x/net v0.10.0 // indirect
 	golang.org/x/sys v0.8.0 // indirect
 	golang.org/x/text v0.9.0 // indirect
-	golang.org/x/tools v0.8.0 // indirect
+	golang.org/x/tools v0.9.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 )
--- a/go.sum
+++ b/go.sum
@@ -20,10 +20,14 @@ github.com/donomii/go-rwkv.cpp v0.0.0-20230503112711-af62fcc432be h1:3Hic97PY6hc
 github.com/donomii/go-rwkv.cpp v0.0.0-20230503112711-af62fcc432be/go.mod h1:gWy7FIWioqYmYxkaoFyBnaKApeZVrUkHhv9EV9pz4dM=
 github.com/donomii/go-rwkv.cpp v0.0.0-20230510174014-07166da10cb2 h1:YNbUAyIRtaLODitigJU1EM5ubmMu5FmHtYAayJD6Vbg=
 github.com/donomii/go-rwkv.cpp v0.0.0-20230510174014-07166da10cb2/go.mod h1:gWy7FIWioqYmYxkaoFyBnaKApeZVrUkHhv9EV9pz4dM=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230515123100-6fdd0c338e56 h1:s8/MZdicstKi5fn9D9mKGIQ/q6IWCYCk/BM68i8v51w=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230515123100-6fdd0c338e56/go.mod h1:gWy7FIWioqYmYxkaoFyBnaKApeZVrUkHhv9EV9pz4dM=
 github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230508180809-bf2449dfae35 h1:sMg/SgnMPS/HNUO/2kGm72vl8R9TmNIwgLFr2TNwR3g=
 github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230508180809-bf2449dfae35/go.mod h1:QIjZ9OktHFG7p+/m3sMvrAJKKdWrr1fZIK0rM6HZlyo=
 github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230509153812-1d17cd5bb37a h1:MlyiDLNCM/wjbv8U5Elj18NvaAgl61SGiRUpqQz5dfs=
 github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230509153812-1d17cd5bb37a/go.mod h1:QIjZ9OktHFG7p+/m3sMvrAJKKdWrr1fZIK0rM6HZlyo=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230515153606-95b02d76b04d h1:uxKTbiRnplE2SubchneSf4NChtxLJtOy9VdHnQMT0d0=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230515153606-95b02d76b04d/go.mod h1:QIjZ9OktHFG7p+/m3sMvrAJKKdWrr1fZIK0rM6HZlyo=
 github.com/go-audio/audio v1.0.0 h1:zS9vebldgbQqktK4H0lUqWrG8P0NxCJVqcj7ZpNnwd4=
 github.com/go-audio/audio v1.0.0/go.mod h1:6uAu0+H2lHkwdGsAY+j2wHPNPpPoeg5AaEFh9FlA+Zs=
 github.com/go-audio/riff v1.0.0 h1:d8iCGbDvox9BfLagY94fBynxSPHO80LmZCaOsmKxokA=
@@ -44,16 +48,24 @@ github.com/go-openapi/swag v0.19.15 h1:D2NRCBzS9/pEY3gP9Nl8aDqGUcPFrwG2p+CNFrLyr
 github.com/go-openapi/swag v0.19.15/go.mod h1:QYRuS/SOXUCsnplDa677K7+DxSOj6IPNl/eQntq43wQ=
 github.com/go-skynet/bloomz.cpp v0.0.0-20230510195113-ad7e89a0885f h1:GW8RQa1RVeDF1dOuAP/y6xWVC+BRtf9tJOuEza6Asbg=
 github.com/go-skynet/bloomz.cpp v0.0.0-20230510195113-ad7e89a0885f/go.mod h1:wc0fJ9V04yiYTfgKvE5RUUSRQ5Kzi0Bo4I+U3nNOUuA=
+github.com/go-skynet/bloomz.cpp v0.0.0-20230510223001-e9366e82abdf h1:VJfSn8hIDE+K5+h38M3iAyFXrxpRExMKRdTk33UDxsw=
+github.com/go-skynet/bloomz.cpp v0.0.0-20230510223001-e9366e82abdf/go.mod h1:wc0fJ9V04yiYTfgKvE5RUUSRQ5Kzi0Bo4I+U3nNOUuA=
 github.com/go-skynet/go-bert.cpp v0.0.0-20230510101404-7bb183b147ea h1:8Isk9D+Auth5OuXVAQPC3MO+5zF/2S7mvs2JZLw6a+8=
 github.com/go-skynet/go-bert.cpp v0.0.0-20230510101404-7bb183b147ea/go.mod h1:NHwIVvsg7Jh6p0M4uBLVmSMEaPUia6O6yjXUpLWVJmQ=
 github.com/go-skynet/go-bert.cpp v0.0.0-20230510124618-ec771ec71557 h1:LD66fKtvP2lmyuuKL8pBat/pVTKUbLs3L5fM/5lyi4w=
 github.com/go-skynet/go-bert.cpp v0.0.0-20230510124618-ec771ec71557/go.mod h1:NHwIVvsg7Jh6p0M4uBLVmSMEaPUia6O6yjXUpLWVJmQ=
+github.com/go-skynet/go-bert.cpp v0.0.0-20230516063724-cea1ed76a7f4 h1:+3KPDf4Wv1VHOkzAfZnlj9qakLSYggTpm80AswhD/FU=
+github.com/go-skynet/go-bert.cpp v0.0.0-20230516063724-cea1ed76a7f4/go.mod h1:VY0s5KoAI2jRCvQXKuDeEEe8KG7VaWifSNJSk+E1KtY=
 github.com/go-skynet/go-gpt2.cpp v0.0.0-20230509180201-d49823284cc6 h1:XshpypO6ekU09CI19vuzke2a1Es1lV5ZaxA7CUehu0E=
 github.com/go-skynet/go-gpt2.cpp v0.0.0-20230509180201-d49823284cc6/go.mod h1:1Wj/xbkMfwQSOrhNYK178IzqQHstZbRfhx4s8p1M5VM=
+github.com/go-skynet/go-gpt2.cpp v0.0.0-20230512145559-7bff56f02245 h1:IcfYY5uH0DdDXEJKJ8bq0WZCd9guPPd3xllaWNy8LOk=
+github.com/go-skynet/go-gpt2.cpp v0.0.0-20230512145559-7bff56f02245/go.mod h1:1Wj/xbkMfwQSOrhNYK178IzqQHstZbRfhx4s8p1M5VM=
 github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230422090028-1f7bff57f66c h1:48I7jpLNGiQeBmF0SFVVbREh8vlG0zN13v9LH5ctXis=
 github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230422090028-1f7bff57f66c/go.mod h1:5VZ9XbcINI0XcHhkcX8GPK8TplFGAzu1Hrg4tNiMCtI=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230510072905-70593fccbe4b h1:qqxrjY8fYDXQahmCMTCACahm1tbiqHLPUHALkFLyBfo=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230510072905-70593fccbe4b/go.mod h1:DLfsPD7tYYnpksERH83HSf7qVNW3FIwmz7/zfYO0/6I=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84 h1:f5iYF75bAr73Tl8AdtFD5Urs/2bsHKPh52K++jLbsfk=
+github.com/go-skynet/go-llama.cpp v0.0.0-20230516230554-b7bbefbe0b84/go.mod h1:jxyQ26t1aKC5Gn782w9WWh5n1133PxCOfkuc01xM4RQ=
 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=
@@ -93,10 +105,18 @@ github.com/mattn/go-isatty v0.0.18 h1:DOKFKCQ7FNG2L1rbrmstDN4QVRdS89Nkh85u68Uwp9
 github.com/mattn/go-isatty v0.0.18/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-runewidth v0.0.14 h1:+xnbZSEeDbOIg5/mE6JF0w6n9duR1l3/WmbinWVwUuU=
 github.com/mattn/go-runewidth v0.0.14/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
+github.com/mudler/go-stable-diffusion v0.0.0-20230516104333-2f32a16b5b24 h1:XfRD/bZom6u4zji7aB0urIVOsPe43KlkzSRrVhlzaOM=
+github.com/mudler/go-stable-diffusion v0.0.0-20230516104333-2f32a16b5b24/go.mod h1:8ufRkpz/S/9ahkaxzZ5i4WMgO9w4InEhuRoT7vK5Rnw=
+github.com/mudler/go-stable-diffusion v0.0.0-20230516152536-c0748eca3642 h1:KTkh3lOUsGqQyP4v+oa38sPFdrZtNnM4HaxTb3epdYs=
+github.com/mudler/go-stable-diffusion v0.0.0-20230516152536-c0748eca3642/go.mod h1:8ufRkpz/S/9ahkaxzZ5i4WMgO9w4InEhuRoT7vK5Rnw=
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e h1:fD57ERR4JtEqsWbfPhv4DMiApHyliiK5xCTNVSPiaAs=
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230516143155-79d6243fe1bc h1:OPavP/SUsVWVYPhSUZKZeX8yDSQzf4G+BmUmwzrLTyI=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20230516143155-79d6243fe1bc/go.mod h1:4T3CHXyrt+7FQHXaxULZfPjHbD8/99WuDDJa0YVZARI=
 github.com/onsi/ginkgo/v2 v2.9.4 h1:xR7vG4IXt5RWx6FfIjyAtsoMAtnc3C/rFXBBd2AjZwE=
 github.com/onsi/ginkgo/v2 v2.9.4/go.mod h1:gCQYp2Q+kSoIj7ykSVb9nskRSsR6PUj4AiLywzIhbKM=
+github.com/onsi/ginkgo/v2 v2.9.5 h1:+6Hr4uxzP4XIUyAkg61dWBw8lb/gc4/X5luuxN/EC+Q=
+github.com/onsi/ginkgo/v2 v2.9.5/go.mod h1:tvAoo1QUJwNEU2ITftXTpR7R1RbCzoZUOs3RonqW57k=
 github.com/onsi/gomega v1.27.6 h1:ENqfyGeS5AX/rlXDd/ETokDz93u0YufY1Pgxuy/PvWE=
 github.com/onsi/gomega v1.27.6/go.mod h1:PIQNjfQwkP3aQAH7lf7j87O/5FiNr+ZR8+ipb+qQlhg=
 github.com/otiai10/copy v1.11.0 h1:OKBD80J/mLBrwnzXqGtFCzprFSGioo30JcmR4APsNwc=
@@ -164,6 +184,8 @@ golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug
 golang.org/x/net v0.3.0/go.mod h1:MBQ8lrhLObU/6UmLb4fmbmk5OcyYmqtbGd/9yIeKjEE=
 golang.org/x/net v0.9.0 h1:aWJ/m6xSmxWBx+V0XRHTlrYrPG56jKsLdTFmsSsCzOM=
 golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
+golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -201,6 +223,8 @@ golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc
 golang.org/x/tools v0.4.0/go.mod h1:UE5sM2OK9E/d67R0ANs2xJizIymRP5gJU295PvKXxjQ=
 golang.org/x/tools v0.8.0 h1:vSDcovVPld282ceKgDimkRSC8kpaH1dgyc9UMzlt84Y=
 golang.org/x/tools v0.8.0/go.mod h1:JxBZ99ISMI5ViVkT1tr6tdNmXeTrcpVSD3vZ1RsRdN4=
+golang.org/x/tools v0.9.1 h1:8WMNJAz3zrtPmnYC7ISf5dEn3MT0gY7jBJfw27yrrLo=
+golang.org/x/tools v0.9.1/go.mod h1:owI94Op576fPu3cIGQeHs3joujW/2Oc6MtlxbF5dfNc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
--- a/main.go
+++ b/main.go
@@ -56,12 +56,24 @@ func main() {
 				EnvVars:     []string{"ADDRESS"},
 				Value:       ":8080",
 			},
+			&cli.StringFlag{
+				Name:        "image-dir",
+				DefaultText: "Image directory",
+				EnvVars:     []string{"IMAGE_DIR"},
+				Value:       "",
+			},
 			&cli.IntFlag{
 				Name:        "context-size",
 				DefaultText: "Default context size of the model",
 				EnvVars:     []string{"CONTEXT_SIZE"},
 				Value:       512,
 			},
+			&cli.IntFlag{
+				Name:        "upload-limit",
+				DefaultText: "Default upload-limit. MB",
+				EnvVars:     []string{"UPLOAD_LIMIT"},
+				Value:       15,
+			},
 		},
 		Description: `
 LocalAI is a drop-in replacement OpenAI API which runs inference locally.
@@ -81,7 +93,7 @@ It uses llama.cpp, ggml and gpt4all as backend with golang c bindings.
 		Copyright: "go-skynet authors",
 		Action: func(ctx *cli.Context) error {
 			fmt.Printf("Starting LocalAI using %d threads, with models path: %s\n", ctx.Int("threads"), ctx.String("models-path"))
-			return api.App(ctx.String("config-file"), model.NewModelLoader(ctx.String("models-path")), ctx.Int("threads"), ctx.Int("context-size"), ctx.Bool("f16"), ctx.Bool("debug"), false).Listen(ctx.String("address"))
+			return api.App(ctx.String("config-file"), model.NewModelLoader(ctx.String("models-path")), ctx.Int("upload-limit"), ctx.Int("threads"), ctx.Int("context-size"), ctx.Bool("f16"), ctx.Bool("debug"), false, ctx.String("image-dir")).Listen(ctx.String("address"))
 		},
 	}

--- a/pkg/model/initializers.go
+++ b/pkg/model/initializers.go
@@ -2,35 +2,40 @@ package model

 import (
 	"fmt"
+	"path/filepath"
 	"strings"

 	rwkv "github.com/donomii/go-rwkv.cpp"
 	whisper "github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
+	"github.com/go-skynet/LocalAI/pkg/stablediffusion"
 	bloomz "github.com/go-skynet/bloomz.cpp"
 	bert "github.com/go-skynet/go-bert.cpp"
 	gpt2 "github.com/go-skynet/go-gpt2.cpp"
 	llama "github.com/go-skynet/go-llama.cpp"
 	"github.com/hashicorp/go-multierror"
-	gpt4all "github.com/nomic/gpt4all/gpt4all-bindings/golang"
+	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
 	"github.com/rs/zerolog/log"
 )

 const tokenizerSuffix = ".tokenizer.json"

 const (
-	LlamaBackend          = "llama"
-	BloomzBackend         = "bloomz"
-	StarcoderBackend      = "starcoder"
-	StableLMBackend       = "stablelm"
-	DollyBackend          = "dolly"
-	RedPajamaBackend      = "redpajama"
-	Gpt2Backend           = "gpt2"
-	Gpt4AllLlamaBackend   = "gpt4all-llama"
-	Gpt4AllMptBackend     = "gpt4all-mpt"
-	Gpt4AllJBackend       = "gpt4all-j"
-	BertEmbeddingsBackend = "bert-embeddings"
-	RwkvBackend           = "rwkv"
-	WhisperBackend        = "whisper"
+	LlamaBackend           = "llama"
+	BloomzBackend          = "bloomz"
+	StarcoderBackend       = "starcoder"
+	StableLMBackend        = "stablelm"
+	DollyBackend           = "dolly"
+	RedPajamaBackend       = "redpajama"
+	GPTNeoXBackend         = "gptneox"
+	ReplitBackend          = "replit"
+	Gpt2Backend            = "gpt2"
+	Gpt4AllLlamaBackend    = "gpt4all-llama"
+	Gpt4AllMptBackend      = "gpt4all-mpt"
+	Gpt4AllJBackend        = "gpt4all-j"
+	BertEmbeddingsBackend  = "bert-embeddings"
+	RwkvBackend            = "rwkv"
+	WhisperBackend         = "whisper"
+	StableDiffusionBackend = "stablediffusion"
 )

 var backends []string = []string{
@@ -45,6 +50,8 @@ var backends []string = []string{
 	StableLMBackend,
 	DollyBackend,
 	RedPajamaBackend,
+	ReplitBackend,
+	GPTNeoXBackend,
 	BertEmbeddingsBackend,
 	StarcoderBackend,
 }
@@ -61,6 +68,14 @@ var dolly = func(modelFile string) (interface{}, error) {
 	return gpt2.NewDolly(modelFile)
 }

+var gptNeoX = func(modelFile string) (interface{}, error) {
+	return gpt2.NewGPTNeoX(modelFile)
+}
+
+var replit = func(modelFile string) (interface{}, error) {
+	return gpt2.NewReplit(modelFile)
+}
+
 var stableLM = func(modelFile string) (interface{}, error) {
 	return gpt2.NewStableLM(modelFile)
 }
@@ -76,6 +91,10 @@ var gpt2LM = func(modelFile string) (interface{}, error) {
 	return gpt2.New(modelFile)
 }

+var stableDiffusion = func(assetDir string) (interface{}, error) {
+	return stablediffusion.New(assetDir)
+}
+
 var whisperModel = func(modelFile string) (interface{}, error) {
 	return whisper.New(modelFile)
 }
@@ -94,6 +113,8 @@ func gpt4allLM(opts ...gpt4all.ModelOption) func(string) (interface{}, error) {

 func rwkvLM(tokenFile string, threads uint32) func(string) (interface{}, error) {
 	return func(s string) (interface{}, error) {
+		log.Debug().Msgf("Loading RWKV", s, tokenFile)
+
 		model := rwkv.LoadFiles(s, tokenFile, threads)
 		if model == nil {
 			return nil, fmt.Errorf("could not load model")
@@ -103,6 +124,7 @@ func rwkvLM(tokenFile string, threads uint32) func(string) (interface{}, error)
 }

 func (ml *ModelLoader) BackendLoader(backendString string, modelFile string, llamaOpts []llama.ModelOption, threads uint32) (model interface{}, err error) {
+	log.Debug().Msgf("Loading model %s from %s", backendString, modelFile)
 	switch strings.ToLower(backendString) {
 	case LlamaBackend:
 		return ml.LoadModel(modelFile, llamaLM(llamaOpts...))
@@ -116,6 +138,12 @@ func (ml *ModelLoader) BackendLoader(backendString string, modelFile string, lla
 		return ml.LoadModel(modelFile, redPajama)
 	case Gpt2Backend:
 		return ml.LoadModel(modelFile, gpt2LM)
+	case GPTNeoXBackend:
+		return ml.LoadModel(modelFile, gptNeoX)
+	case ReplitBackend:
+		return ml.LoadModel(modelFile, replit)
+	case StableDiffusionBackend:
+		return ml.LoadModel(modelFile, stableDiffusion)
 	case StarcoderBackend:
 		return ml.LoadModel(modelFile, starCoder)
 	case Gpt4AllLlamaBackend:
@@ -127,7 +155,7 @@ func (ml *ModelLoader) BackendLoader(backendString string, modelFile string, lla
 	case BertEmbeddingsBackend:
 		return ml.LoadModel(modelFile, bertEmbeddings)
 	case RwkvBackend:
-		return ml.LoadModel(modelFile, rwkvLM(modelFile+tokenizerSuffix, threads))
+		return ml.LoadModel(modelFile, rwkvLM(filepath.Join(ml.ModelPath, modelFile+tokenizerSuffix), threads))
 	case WhisperBackend:
 		return ml.LoadModel(modelFile, whisperModel)
 	default:
--- a/pkg/stablediffusion/generate.go
+++ b/pkg/stablediffusion/generate.go
@@ -0,0 +1,23 @@
+//go:build stablediffusion
+// +build stablediffusion
+
+package stablediffusion
+
+import (
+	stableDiffusion "github.com/mudler/go-stable-diffusion"
+)
+
+func GenerateImage(height, width, mode, step, seed int, positive_prompt, negative_prompt, dst, asset_dir string) error {
+	return stableDiffusion.GenerateImage(
+		height,
+		width,
+		mode,
+		step,
+		seed,
+		positive_prompt,
+		negative_prompt,
+		dst,
+		"",
+		asset_dir,
+	)
+}
--- a/pkg/stablediffusion/generate_unsupported.go
+++ b/pkg/stablediffusion/generate_unsupported.go
@@ -0,0 +1,10 @@
+//go:build !stablediffusion
+// +build !stablediffusion
+
+package stablediffusion
+
+import "fmt"
+
+func GenerateImage(height, width, mode, step, seed int, positive_prompt, negative_prompt, dst, asset_dir string) error {
+	return fmt.Errorf("This version of LocalAI was built without the stablediffusion tag")
+}
--- a/pkg/stablediffusion/stablediffusion.go
+++ b/pkg/stablediffusion/stablediffusion.go
@@ -0,0 +1,20 @@
+package stablediffusion
+
+import "os"
+
+type StableDiffusion struct {
+	assetDir string
+}
+
+func New(assetDir string) (*StableDiffusion, error) {
+	if _, err := os.Stat(assetDir); err != nil {
+		return nil, err
+	}
+	return &StableDiffusion{
+		assetDir: assetDir,
+	}, nil
+}
+
+func (s *StableDiffusion) GenerateImage(height, width, mode, step, seed int, positive_prompt, negative_prompt, dst string) error {
+	return GenerateImage(height, width, mode, step, seed, positive_prompt, negative_prompt, dst, s.assetDir)
+}
--- a/pkg/whisper/whisper.go
+++ b/pkg/whisper/whisper.go
@@ -28,7 +28,7 @@ func audioToWav(src, dst string) error {
 	return nil
 }

-func Transcript(model whisper.Model, audiopath, language string) (string, error) {
+func Transcript(model whisper.Model, audiopath, language string, threads uint) (string, error) {

 	dir, err := os.MkdirTemp("", "whisper")
 	if err != nil {
@@ -65,8 +65,12 @@ func Transcript(model whisper.Model, audiopath, language string) (string, error)

 	}

+	context.SetThreads(threads)
+
 	if language != "" {
 		context.SetLanguage(language)
+	} else {
+		context.SetLanguage("auto")
 	}

 	if err := context.Process(data, nil); err != nil {
--- a/tests/fixtures/embeddings.yaml
+++ b/tests/fixtures/embeddings.yaml
@@ -0,0 +1,6 @@
+name: text-embedding-ada-002
+parameters:
+  model: bert
+threads: 14
+backend: bert-embeddings
+embeddings: true
--- a/tests/fixtures/rwkv.yaml
+++ b/tests/fixtures/rwkv.yaml
@@ -0,0 +1,19 @@
+name: rwkv_test
+parameters:
+  model: rwkv
+  top_k: 80
+  temperature: 0.9
+  max_tokens: 100
+  top_p: 0.8
+context_size: 1024
+threads: 14
+backend: "rwkv"
+cutwords:
+- "Bob:.*"
+roles:
+  user: "Bob:"
+  system: "Alice:"
+  assistant: "Alice:"
+template:
+  completion: rwkv_completion
+  chat: rwkv_chat
--- a/tests/fixtures/rwkv_chat.tmpl
+++ b/tests/fixtures/rwkv_chat.tmpl
@@ -0,0 +1,13 @@
+The following is a verbose detailed conversation between Bob and a woman, Alice. Alice is intelligent, friendly and likeable. Alice is likely to agree with Bob.
+
+Bob: Hello Alice, how are you doing?
+
+Alice: Hi Bob! Thanks, I'm fine. What about you?
+
+Bob: I am very good! It's nice to see you. Would you mind me chatting with you for a while?
+
+Alice: Not at all! I'm listening.
+
+{{.Input}}
+
+Alice: 
--- a/tests/fixtures/rwkv_completion.tmpl
+++ b/tests/fixtures/rwkv_completion.tmpl
@@ -0,0 +1 @@
+Complete the following sentence: {{.Input}} 
--- a/tests/fixtures/whisper.yaml
+++ b/tests/fixtures/whisper.yaml
@@ -0,0 +1,4 @@
+name: whisper-1
+backend: whisper
+parameters:
+  model: whisper-en
Author	SHA1	Message	Date
Ettore Di Giacinto	3f739575d8	Minor fixes (#285 )	2023-05-17 21:01:46 +02:00
ci-robbot [bot]	7e4616646f	⬆️ Update go-skynet/go-bert.cpp (#274 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-17 11:56:32 +02:00
renovate[bot]	44ffaf86ad	fix(deps): update github.com/go-skynet/go-llama.cpp digest to b7bbefb (#243 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 11:52:54 +02:00
renovate[bot]	d096644c67	fix(deps): update github.com/go-skynet/go-gpt2.cpp digest to 7bff56f (#217 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 11:52:37 +02:00
renovate[bot]	1428600de4	fix(deps): update github.com/go-skynet/go-bert.cpp digest to cea1ed7 (#242 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 09:47:22 +02:00
renovate[bot]	17b18df600	fix(deps): update github.com/donomii/go-rwkv.cpp digest to 6fdd0c3 (#240 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 08:54:52 +02:00
renovate[bot]	cd81dbae1c	fix(deps): update github.com/go-skynet/bloomz.cpp digest to e9366e8 (#227 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 08:17:05 +02:00
ci-robbot [bot]	76be06ed56	⬆️ Update go-skynet/go-gpt2.cpp (#253 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-17 01:47:31 +02:00
renovate[bot]	c2026e01c0	fix(deps): update github.com/mudler/go-stable-diffusion digest to c0748ec (#275 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 01:44:14 +02:00
Ettore Di Giacinto	cdca286be1	docker: add openblas and opencv to images (#277 )	2023-05-17 01:30:30 +02:00
ci-robbot [bot]	41de6efca9	⬆️ Update ggerganov/whisper.cpp (#265 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-17 01:04:14 +02:00
renovate[bot]	63a4ccebdc	fix(deps): update module github.com/onsi/ginkgo/v2 to v2.9.5 (#264 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-17 01:03:43 +02:00
renovate[bot]	9237c1e91d	fix(deps): update github.com/ggerganov/whisper.cpp/bindings/go digest to 95b02d7 (#254 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2023-05-16 22:34:36 +02:00
Ettore Di Giacinto	9d051c5d4f	feat: add image generation with ncnn-stablediffusion (#272 )	2023-05-16 19:32:53 +02:00
Ettore Di Giacinto	acd03d15f2	feat: add support for cublas/openblas in the llama.cpp backend (#258 )	2023-05-16 16:26:25 +02:00
Ettore Di Giacinto	a035de2fdd	tests: add rwkv (#261 )	2023-05-15 08:15:01 +02:00
Ettore Di Giacinto	76a1267799	bump: update whisper.cpp (#260 )	2023-05-15 01:00:16 +02:00
Ettore Di Giacinto	e533b008d4	docs: update README	2023-05-14 18:09:26 +02:00
Ettore Di Giacinto	a4380228e3	docs: update README	2023-05-14 18:08:42 +02:00
Ettore Di Giacinto	2a9d7474ce	fix(rwkv): load tokenizer file from model path (#255 )	2023-05-14 17:49:10 +02:00
Ettore Di Giacinto	850a690290	docs: update README	2023-05-14 11:14:09 +02:00
Ettore Di Giacinto	39edd9ff73	docs: update README short-term roadmap	2023-05-14 11:12:29 +02:00
ci-robbot [bot]	b82bbbfc6b	⬆️ Update ggerganov/whisper.cpp (#218 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-14 10:03:55 +02:00
mudler	023c065812	docs: Fix typo	2023-05-13 22:14:35 +02:00
mudler	a627a6c4e2	docs: Update README	2023-05-13 22:14:09 +02:00
ci-robbot [bot]	6c9ddff8e9	⬆️ Update go-skynet/go-llama.cpp (#245 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-13 22:07:43 +02:00
ci-robbot [bot]	c5318587b8	⬆️ Update go-skynet/go-bert.cpp (#247 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-13 14:36:01 +02:00
mudler	c3622299ce	docs: cleanup langchain-chroma example	2023-05-13 11:16:56 +02:00
Ettore Di Giacinto	de36a48861	Update gpt4all to fix thread counts (#249 )	2023-05-13 09:37:46 +02:00
mudler	961ca93219	docs: Update README	2023-05-13 00:46:48 +02:00
Ettore Di Giacinto	557ccc5ad8	examples: add langchain-chroma example (#248 )	2023-05-12 22:20:07 +02:00
Ettore Di Giacinto	2488c445b6	feat: bert.cpp token embeddings (#241 )	2023-05-12 17:16:49 +02:00
Ettore Di Giacinto	b4241d0a0d	tests: enable whisper (#239 )	2023-05-12 14:10:18 +02:00
Ettore Di Giacinto	8250391e49	Add support for gptneox/replit (#238 )	2023-05-12 11:36:35 +02:00
Ettore Di Giacinto	fd1df4e971	whisper: add tests and allow to set upload size (#237 )	2023-05-12 10:04:20 +02:00
ci-robbot [bot]	5115b2faa3	⬆️ Update go-skynet/go-llama.cpp (#219 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-11 23:43:55 +02:00
ci-robbot [bot]	93e82a8bf4	⬆️ Update go-skynet/go-gpt2.cpp (#220 ) Signed-off-by: GitHub <noreply@github.com> Co-authored-by: mudler <mudler@users.noreply.github.com>	2023-05-11 23:43:44 +02:00
				`@@ -0,0 +1 @@`
				`Complete the following sentence: {{.Input}}`