diff --git a/packs/local-ai-2.18.1/README.md b/packs/local-ai-2.18.1/README.md new file mode 100644 index 0000000..59125f4 --- /dev/null +++ b/packs/local-ai-2.18.1/README.md @@ -0,0 +1,52 @@ +**LocalAI** is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that’s compatible with OpenAI (Elevenlabs, Anthropic... ) API specifications for local AI inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families. Does not require GPU. It is created and maintained by [Ettore Di Giacinto](https://github.com/mudler). + + +## [πŸ’» Get Started here!](https://localai.io/basics/getting_started/index.html) + + +## πŸš€ [Features](https://localai.io/features/) + +- πŸ“– [Text generation with GPTs](https://localai.io/features/text-generation/) (`llama.cpp`, `gpt4all.cpp`, ... [:book: and more](https://localai.io/model-compatibility/index.html#model-compatibility-table)) +- πŸ—£ [Text to Audio](https://localai.io/features/text-to-audio/) +- πŸ”ˆ [Audio to Text](https://localai.io/features/audio-to-text/) (Audio transcription with `whisper.cpp`) +- 🎨 [Image generation with stable diffusion](https://localai.io/features/image-generation) +- πŸ”₯ [OpenAI-alike tools API](https://localai.io/features/openai-functions/) +- 🧠 [Embeddings generation for vector databases](https://localai.io/features/embeddings/) +- ✍️ [Constrained grammars](https://localai.io/features/constrained_grammars/) +- πŸ–ΌοΈ [Download Models directly from Huggingface ](https://localai.io/models/) +- πŸ₯½ [Vision API](https://localai.io/features/gpt-vision/) +- πŸ“ˆ [Reranker API](https://localai.io/features/reranker/) +- πŸ†•πŸ–§ [P2P Inferencing](https://localai.io/features/distribute/) + +### πŸ”— Resources + +- [LLM finetuning guide](https://localai.io/docs/advanced/fine-tuning/) +- [How to build locally](https://localai.io/basics/build/index.html) +- [How to install in Kubernetes](https://localai.io/basics/getting_started/index.html#run-localai-in-kubernetes) +- [Projects integrating LocalAI](https://localai.io/docs/integrations/) +- [How tos section](https://io.midori-ai.xyz/howtos/) (curated by our community) + +### πŸ”— Community and integrations + +Build and deploy custom containers: +- https://github.com/sozercan/aikit + +WebUIs: +- https://github.com/Jirubizu/localai-admin +- https://github.com/go-skynet/LocalAI-frontend +- QA-Pilot(An interactive chat project that leverages LocalAI LLMs for rapid understanding and navigation of GitHub code repository) https://github.com/reid41/QA-Pilot + +Model galleries +- https://github.com/go-skynet/model-gallery + +Other: +- Helm chart https://github.com/go-skynet/helm-charts +- VSCode extension https://github.com/badgooooor/localai-vscode-plugin +- Terminal utility https://github.com/djcopley/ShellOracle +- Local Smart assistant https://github.com/mudler/LocalAGI +- Home Assistant https://github.com/sammcj/homeassistant-localai / https://github.com/drndos/hass-openai-custom-conversation / https://github.com/valentinfrlch/ha-gpt4vision +- Discord bot https://github.com/mudler/LocalAGI/tree/main/examples/discord +- Slack bot https://github.com/mudler/LocalAGI/tree/main/examples/slack +- Shell-Pilot(Interact with LLM using LocalAI models via pure shell scripts on your Linux or MacOS system) https://github.com/reid41/shell-pilot +- Telegram bot https://github.com/mudler/LocalAI/tree/master/examples/telegram-bot +- Examples: https://github.com/mudler/LocalAI/tree/master/examples/ \ No newline at end of file diff --git a/packs/local-ai-2.18.1/charts/local-ai-3.3.0.tgz b/packs/local-ai-2.18.1/charts/local-ai-3.3.0.tgz new file mode 100644 index 0000000..ceb594c Binary files /dev/null and b/packs/local-ai-2.18.1/charts/local-ai-3.3.0.tgz differ diff --git a/packs/local-ai-2.18.1/logo.png b/packs/local-ai-2.18.1/logo.png new file mode 100644 index 0000000..9628a2d Binary files /dev/null and b/packs/local-ai-2.18.1/logo.png differ diff --git a/packs/local-ai-2.18.1/pack.json b/packs/local-ai-2.18.1/pack.json new file mode 100644 index 0000000..fd06fc1 --- /dev/null +++ b/packs/local-ai-2.18.1/pack.json @@ -0,0 +1,18 @@ +{ + "addonType": "system app", + "annotations": { + "commit_msg": "LocalAI - The free, Open Source OpenAI alternative", + "source": "community", + "contributor" : "pedro@spectrocloud" + }, + "charts": [ + "charts/local-ai-3.3.0.tgz" + ], + "cloudTypes": [ + "all" + ], + "displayName": "LocalAI", + "layer":"addon", + "name": "local-ai", + "version": "2.18.1" +} \ No newline at end of file diff --git a/packs/local-ai-2.18.1/values.yaml b/packs/local-ai-2.18.1/values.yaml new file mode 100644 index 0000000..6c75310 --- /dev/null +++ b/packs/local-ai-2.18.1/values.yaml @@ -0,0 +1,161 @@ +# Default values for eck-elastic-operator +# This is a YAML-formatted file +pack: + content: + images: + - image: quay.io/go-skynet/local-ai:v2.18.1 + + charts: + - repo: https://go-skynet.github.io/helm-charts/ + name: local-ai + version: 3.3.0 + #The namespace (on the target cluster) to install this chart + #When not found, a new namespace will be created + namespace: "local-ui" + +charts: + local-ai: + fullnameOverride: local-ai + + replicaCount: 1 + + deployment: + # For Nvidia GPUs uncomment one of the following (cuda11 or cuda12): + # image: localai/localai:v2.18.1-cublas-cuda11 + # image: localai/localai:v2.18.1-cublas-cuda12 + # image: localai/localai:v2.18.1-cublas-cuda11-ffmpeg (Video Acceleration) + # image: localai/localai:v2.18.1-cublas-cuda12-ffmpeg (Video Acceleration) + # More info in Docs: https://localai.io/features/gpu-acceleration/#cudanvidia-acceleration + image: + repository: quay.io/go-skynet/local-ai # Example: "docker.io/myapp" + tag: v2.18.1 + env: + threads: 4 + context_size: 512 + + # # Inject Secrets into Environment: + # secretEnv: + # - name: HF_TOKEN + # valueFrom: + # secretKeyRef: + # name: some-secret + # key: hf-token + + modelsPath: "/models" + download_model: + # To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox + image: busybox + prompt_templates: + # To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox + image: busybox + pullPolicy: IfNotPresent + imagePullSecrets: [] + # - name: secret-names + + ## Needed for GPU Nodes + #runtimeClassName: gpu + + resources: + {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + # Prompt templates to include + # Note: the keys of this map will be the names of the prompt template files + promptTemplates: + {} + # ggml-gpt4all-j.tmpl: | + # 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: + + # Models to download at runtime + models: + # Whether to force download models even if they already exist + forceDownload: false + + # The list of URLs to download models from + # Note: the name of the file will be the name of the loaded model + list: + # - url: "https://gpt4all.io/models/ggml-gpt4all-j.bin" + # basicAuth: base64EncodedCredentials + + initContainers: [] + # Example: + # - name: my-init-container + # image: my-init-image + # imagePullPolicy: IfNotPresent + # command: ["/bin/sh", "-c", "echo init"] + # volumeMounts: + # - name: my-volume + # mountPath: /path/to/mount + + sidecarContainers: [] + # Example: + # - name: my-sidecar-container + # image: my-sidecar-image + # imagePullPolicy: IfNotPresent + # ports: + # - containerPort: 1234 + + # Persistent storage for models and prompt templates. + # PVC and HostPath are mutually exclusive. If both are enabled, + # PVC configuration takes precedence. If neither are enabled, ephemeral + # storage is used. + persistence: + models: + enabled: true + annotations: {} + storageClass: hostPath + accessModes: ReadWriteMany + size: 10Gi + globalMount: /models + output: + enabled: true + annotations: {} + storageClass: hostPath + accessModes: ReadWriteMany + size: 5Gi + globalMount: /tmp/generated + + service: + type: ClusterIP + # If deferring to an internal only load balancer + # externalTrafficPolicy: Local + port: 80 + annotations: {} + # If using an AWS load balancer, you'll need to override the default 60s load balancer idle timeout + # service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200" + + ingress: + enabled: false + className: "" + annotations: + {} + # nginx.ingress.kubernetes.io/proxy-body-size: "25m" # This value determines the maxmimum uploadable file size + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + hosts: + - host: chart-example.local + paths: + - path: / + pathType: ImplementationSpecific + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + + nodeSelector: {} + + tolerations: [] + + affinity: {} \ No newline at end of file