base on # local-llm Run LLMs locally on Cloud Workstations. Uses: - Quantized models from 🤗 - [llama-cpp-python's webserver][web-server] In this guide: * [Running as a Cloud Workstation](#running-as-a-cloud-workstation) * [local-llm commands](#local-llm-commands) * [Running locally](#running-locally) * [Debugging](#debugging) * [LLM disclaimer](#llm-disclaimer) ## Running as a [Cloud Workstation][cw] This repository includes a [Dockerfile](./Dockerfile) that can be used to create a [custom base image][cw-custom] for a Cloud Workstation environment that includes the `llm` tool. To get started, you'll need to have a [GCP Project][gcp] and have the `gcloud` CLI [installed][gcloud]. 1. Set environment variables 1. Set the `PROJECT_ID` and `PROJECT_NUM` environment variables from your GCP project. You must modify the values. ```shell export PROJECT_ID=<project-id> export PROJECT_NUM=<project-num> ``` 1. Set other needed environment variables. You can modify the values. ```shell export REGION=us-central1 export LOCALLLM_REGISTRY=localllm-registry export LOCALLLM_IMAGE_NAME=localllm export LOCALLLM_CLUSTER=localllm-cluster export LOCALLLM_WORKSTATION=localllm-workstation export LOCALLLM_PORT=8000 ``` 1. Set the default project. ```shell gcloud config set project $PROJECT_ID ``` 1. Enable needed services. ```shell gcloud services enable \ cloudbuild.googleapis.com \ workstations.googleapis.com \ container.googleapis.com \ containeranalysis.googleapis.com \ containerscanning.googleapis.com \ artifactregistry.googleapis.com ``` 1. Create an Artifact Registry repository for docker images. ```shell gcloud artifacts repositories create $LOCALLLM_REGISTRY \ --location=$REGION \ --repository-format=docker ``` 1. Build and push the image to Artifact Registry using Cloud Build. Details are in [cloudbuild.yaml](cloudbuild.yaml). ```shell gcloud builds submit . \ --substitutions=_IMAGE_REGISTRY=$LOCALLLM_REGISTRY,_IMAGE_NAME=$LOCALLLM_IMAGE_NAME ``` 1. Configure a Cloud Workstation cluster. **Wait for this to complete before moving forward** which can take [up to 20 minutes](https://cloud.google.com/workstations/docs/create-cluster#workstation-cluster). ```shell gcloud workstations clusters create $LOCALLLM_CLUSTER \ --region=$REGION ``` 1. Create a Cloud Workstation configuration. We suggest using a machine type of e2-standard-32 which has 32 vCPU, 16 core and 128 GB memory. ```shell gcloud beta workstations configs create $LOCALLLM_WORKSTATION \ --region=$REGION \ --cluster=$LOCALLLM_CLUSTER \ --machine-type=e2-standard-32 \ --container-custom-image=us-central1-docker.pkg.dev/${PROJECT_ID}/${LOCALLLM_REGISTRY}/${LOCALLLM_IMAGE_NAME}:latest ``` 1. Create a Cloud Workstation. ```shell gcloud workstations create $LOCALLLM_WORKSTATION \ --cluster=$LOCALLLM_CLUSTER \ --config=$LOCALLLM_WORKSTATION \ --region=$REGION ``` 1. Grant access to the default Cloud Workstation service account. ```shell gcloud artifacts repositories add-iam-policy-binding $LOCALLLM_REGISTRY \ --location=$REGION \ --member=serviceAccount:service-$PROJECT_NUM@gcp-sa-workstationsvm.iam.gserviceaccount.com \ --role=roles/artifactregistry.reader ``` 1. Start the workstation. ```shell gcloud workstations start $LOCALLLM_WORKSTATION \ --cluster=$LOCALLLM_CLUSTER \ --config=$LOCALLLM_WORKSTATION \ --region=$REGION ``` 1. Connect to the workstation using ssh. Alternatively, you can connect to the workstation [interactively][launch-workstation] in the browser. ```bash gcloud workstations ssh $LOCALLLM_WORKSTATION \ --cluster=$LOCALLLM_CLUSTER \ --config=$LOCALLLM_WORKSTATION \ --region=$REGION ``` 1. Start serving the default model from the repo. ```shell local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF $LOCALLLM_PORT ``` 1. Get the hostname of the workstation using: ```bash gcloud workstations describe $LOCALLLM_WORKSTATION \ --cluster=$LOCALLLM_CLUSTER \ --config=$LOCALLLM_WORKSTATION \ --region=$REGION ``` 1. Interact with the model by visiting the live OpenAPI documentation page: `https://$LOCALLLM_PORT-$LLM_HOSTNAME/docs`. ## local-llm commands [!NOTE] The command is now `local-llm`, however the original command (`llm`) is supported inside of the [cloud workstations image](#running-as-a-cloud-workstation). Assumes that models are downloaded to `~/.cache/huggingface/hub/`. This is the default cache path used by Hugging Face Hub [library][hf-hub] and only supports `.gguf` files. If you're using models from TheBloke and you don't specify a filename, we'll attempt to use the model with 4 bit medium quantization, or you can specify a filename explicitly. 1. List downloaded models. ```shell local-llm list ``` 1. List running models. ```shell local-llm ps ``` 1. Start serving models. 1. Start serving the default model from the repo. Download if not present. ```shell local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF 8000 ``` 1. Start serving a specific model. Download if not present. ```shell local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF --filename llama-2-13b-ensemble-v5.Q4_K_S.gguf 8000 ``` 1. Stop serving models. 1. Stop serving all models from the repo. ```shell local-llm kill TheBloke/Llama-2-13B-Ensemble-v5-GGUF ``` 1. Stop serving a specific model. ```shell local-llm kill TheBloke/Llama-2-13B-Ensemble-v5-GGUF --filename llama-2-13b-ensemble-v5.Q4_K_S.gguf ``` 1. Download models. 1. Download the default model from the repo. ```shell local-llm pull TheBloke/Llama-2-13B-Ensemble-v5-GGUF ``` 1. Download a specific model from the repo. ```shell local-llm pull TheBloke/Llama-2-13B-Ensemble-v5-GGUF --filename llama-2-13b-ensemble-v5.Q4_K_S.gguf ``` 1. Remove models. 1. Remove all models downloaded from the repo. ```shell local-llm rm TheBloke/Llama-2-13B-Ensemble-v5-GGUF ``` 1. Remove a specific model from the repo. ```shell local-llm rm TheBloke/Llama-2-13B-Ensemble-v5-GGUF --filename llama-2-13b-ensemble-v5.Q4_K_S.gguf ``` ## Running locally 1. Install the tools. ```shell # Install the tools pip3 install openai pip3 install ./local-llm/. ``` 1. Download and run a model. ```shell local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF 8000 ``` 1. Try out a query. The default query is for a haiku about cats. ```shell python3 querylocal.py ``` 1. Interact with the Open API interface via the `/docs` extension. For the above, visit http://localhost:8000/docs. ## Debugging To assist with debugging, you can configure model startup to write logs to a log file by providing a yaml python logging configuration file: ``` local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF 8000 --log-config <some config file> ``` To run locally using the bundled log config ([log_config.yaml](../local-llm/log_config.yaml)): ``` sudo touch /var/log/local-llm.log sudo chown user:user /var/log/local-llm.log # use your user and group # provide the log config manually local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF 8000 --log-config local-llm/log_config.yaml # or use an environment variable so you don't have to pass the argument export LOG_CONFIG=$(pip show local-llm | grep Location | awk '{print $2}')/log_config.yaml local-llm run TheBloke/Llama-2-13B-Ensemble-v5-GGUF 8000 ``` You can follow the logs with: ``` tail -f /var/log/local-llm.log ``` If you are running multiple models, the logs from each will be written to the same file and interleaved. If running from Cloud Workstations, logs from running models will be written to `/var/log/local-llm.log` ([log_config.yaml](../local-llm/log_config.yaml) is provided by default via the environment variable `LOG_CONFIG` within the image). ## LLM Disclaimer This project imports freely available LLMs and makes them available from [Cloud Workstations][cw]. We recommend independently verifying any content generated by the models. We do not assume any responsibility or liability for the use or interpretation of generated content. [gcp]: https://cloud.google.com/docs/get-started [gcloud]: https://cloud.google.com/sdk/docs/install [cw]: https://cloud.google.com/workstations [cw-custom]: https://cloud.google.com/workstations/docs/customize-container-images [launch-workstation]: https://cloud.google.com/workstations/docs/create-workstation#launch_a_workstation [hf-hub]: https://github.com/huggingface/huggingface_hub [web-server]: https://github.com/abetlen/llama-cpp-python#web-server ", Assign "at most 3 tags" to the expected json: {"id":"7653","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"