move distribution folders

distributions/ollama/README.md

@@ -1,16 +1,21 @@
-# Ollama GPU Distribution
+# Ollama Distribution
 
-The scripts in these folders help you spin up a Llama Stack distribution with Ollama Inference provider.
+The `llamastack/distribution-ollama` distribution consists of the following provider configurations.
+
+| **API**         	| **Inference**  	| **Agents**     	| **Memory**                       	| **Safety**     	| **Telemetry**  	|
+|-----------------	|----------------	|----------------	|----------------------------------	|----------------	|----------------	|
+| **Provider(s)** 	| remote::ollama 	| meta-reference 	| remote::pgvector, remote::chroma 	| remote::ollama 	| meta-reference 	|
+
+
+### Start a Distribution (Single Node GPU)
 
 > [!NOTE]
-> This assumes you have access to GPU to start a Ollama server with access to your GPU. Please see Ollama CPU Distribution if you wish to run Ollama on CPU.
+> This assumes you have access to GPU to start a Ollama server with access to your GPU.
-
-### Getting Started
 
 ```
-$ cd llama_stack/distribution/docker/ollama
+$ cd llama-stack/distribution/ollama/gpu
 $ ls
-compose.yaml  ollama-run.yaml
+compose.yaml  run.yaml
 $ docker compose up
 ```
 
@@ -22,10 +27,10 @@ INFO:     Started server process [1]
 INFO:     Waiting for application startup.
 INFO:     Application startup complete.
 INFO:     Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
-[llamastack-local-cpu] | Resolved 12 providers
+[llamastack] | Resolved 12 providers
-[llamastack-local-cpu] |  inner-inference => ollama0
+[llamastack] |  inner-inference => ollama0
-[llamastack-local-cpu] |  models => __routing_table__
+[llamastack] |  models => __routing_table__
-[llamastack-local-cpu] |  inference => __autorouted__
+[llamastack] |  inference => __autorouted__
 ```
 
 To kill the server
@@ -33,11 +38,23 @@ To kill the server
 docker compose down
 ```
 
-### (Alternative) Docker Run
+### Start the Distribution (Single Node CPU)
+
+> [!NOTE]
+> This will start an ollama server with CPU only, please see [Ollama Documentations](https://github.com/ollama/ollama) for serving models on CPU only.
+
+```
+$ cd llama-stack/distribution/ollama/cpu
+$ ls
+compose.yaml  run.yaml
+$ docker compose up
+```
+
+### (Alternative) ollama run + llama stack Run
 
 If you wish to separately spin up a Ollama server, and connect with Llama Stack, you may use the following commands.
 
-##### Start Ollama server.
+#### Start Ollama server.
 - Please check the [Ollama Documentations](https://github.com/ollama/ollama) for more details.
 
 **Via Docker**
@@ -50,9 +67,9 @@ docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
 ollama run <model_id>
 ```
 
+#### Start Llama Stack server pointing to Ollama server
 
-##### Start Llama Stack server pointing to Ollama server
+**Via Docker**
-
 ```
 docker run --network host -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./ollama-run.yaml:/root/llamastack-run-ollama.yaml --gpus=all llamastack-local-cpu --yaml_config /root/llamastack-run-ollama.yaml
 ```
@@ -65,3 +82,10 @@ inference:
     config:
       url: http://127.0.0.1:14343
 ```
+
+**Via Conda**
+
+```
+llama stack build --config ./build.yaml
+llama stack run ./gpu/run.yaml
+```

distributions/ollama/build.yaml

@@ -0,0 +1,13 @@
+name: local-ollama
+distribution_spec:
+  description: Like local, but use ollama for running LLM inference
+  providers:
+    inference: remote::ollama
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

distributions/ollama/cpu/compose.yaml

@@ -0,0 +1,30 @@
+services:
+  ollama:
+    image: ollama/ollama:latest
+    network_mode: "host"
+    volumes:
+      - ollama:/root/.ollama # this solution synchronizes with the docker volume and loads the model rocket fast
+    ports:
+      - "11434:11434"
+    command: []
+  llamastack:
+    depends_on:
+    - ollama
+    image: llamastack/llamastack-local-cpu
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      # Link to ollama run.yaml file
+      - ./run.yaml:/root/my-run.yaml
+    ports:
+      - "5000:5000"
+    # Hack: wait for ollama server to start before starting docker
+    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
+volumes:
+  ollama:

distributions/ollama/gpu/run.yaml

@@ -0,0 +1,46 @@
+version: '2'
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
+apis:
+- shields
+- agents
+- models
+- memory
+- memory_banks
+- inference
+- safety
+providers:
+  inference:
+  - provider_id: ollama0
+    provider_type: remote::ollama
+    config:
+      url: http://127.0.0.1:14343
+  safety:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
+  memory:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}
+  agents:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: ~/.llama/runtime/kvstore.db
+  telemetry:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}

distributions/tgi/README.md

@@ -1,11 +1,18 @@
-# TGI GPU Distribution
+# TGI Distribution
 
-The scripts in these folders help you spin up a Llama Stack distribution with TGI Inference provider.
+The `llamastack/distribution-tgi` distribution consists of the following provider configurations.
+
+
+| **API**         	| **Inference** 	| **Agents**     	| **Memory**                                       	| **Safety**     	| **Telemetry**  	|
+|-----------------	|---------------	|----------------	|--------------------------------------------------	|----------------	|----------------	|
+| **Provider(s)** 	| remote::tgi   	| meta-reference 	| meta-reference, remote::pgvector, remote::chroma 	| meta-reference 	| meta-reference 	|
+
+
+### Start the Distribution (Single Node GPU)
 
 > [!NOTE]
-> This assumes you have access to GPU to start a TGI server with access to your GPU. Please see TGI CPU Distribution if you wish connect to a hosted TGI endpoint.
+> This assumes you have access to GPU to start a TGI server with access to your GPU.
 
-### Getting Started
 
 ```
 $ cd llama_stack/distribution/docker/tgi
@@ -30,23 +37,37 @@ To kill the server
 docker compose down
 ```
 
-### (Alternative) Docker Run
+### Start the Distribution (Single Node CPU)
+
+> [!NOTE]
+> This assumes you have an hosted endpoint
+
+```
+$ cd llama-stack/distribution/tgi/cpu
+$ ls
+compose.yaml  run.yaml
+$ docker compose up
+```
+
+### (Alternative) TGI server + llama stack run (Single Node GPU)
 
 If you wish to separately spin up a TGI server, and connect with Llama Stack, you may use the following commands.
 
-##### Start TGI server.
+#### (optional) Start TGI server locally
+- Please check the [TGI Getting Started Guide](https://github.com/huggingface/text-generation-inference?tab=readme-ov-file#get-started) to get a TGI endpoint.
+
 ```
 docker run --rm -it -v $HOME/.cache/huggingface:/data -p 5009:5009 --gpus all ghcr.io/huggingface/text-generation-inference:latest --dtype bfloat16 --usage-stats on --sharded false --model-id meta-llama/Llama-3.1-8B-Instruct --port 5009
 ```
-- Please check the [TGI Getting Started Guide](https://github.com/huggingface/text-generation-inference?tab=readme-ov-file#get-started) for more details.
 
-##### Start Llama Stack server pointing to TGI server
+
+#### Start Llama Stack server pointing to TGI server
 
 ```
-docker run --network host -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./tgi-run.yaml:/root/llamastack-run-tgi.yaml --gpus=all llamastack-local-cpu --yaml_config /root/llamastack-run-tgi.yaml
+docker run --network host -it -p 5000:5000 -v ./run.yaml:/root/my-run.yaml --gpus=all llamastack-local-cpu --yaml_config /root/my-run.yaml
 ```
 
-Make sure in you `tgi-run.yaml` file, you inference provider is pointing to the correct TGI endpoint. E.g.
+Make sure in you `run.yaml` file, you inference provider is pointing to the correct TGI server endpoint. E.g.
 ```
 inference:
   - provider_id: tgi0
@@ -54,3 +75,11 @@ inference:
     config:
       url: http://127.0.0.1:5009
 ```
+
+**Via Conda**
+
+```bash
+llama stack build --config ./build.yaml
+# -- start a TGI server endpoint
+llama stack run ./gpu/run.yaml
+```

distributions/tgi/cpu/compose.yaml

@@ -0,0 +1,54 @@
+services:
+  text-generation-inference:
+    image: ghcr.io/huggingface/text-generation-inference:latest
+    network_mode: "host"
+    volumes:
+      - $HOME/.cache/huggingface:/data
+    ports:
+      - "5009:5009"
+    devices:
+      - nvidia.com/gpu=all
+    environment:
+      - CUDA_VISIBLE_DEVICES=0
+      - HF_HOME=/data
+      - HF_DATASETS_CACHE=/data
+      - HF_MODULES_CACHE=/data
+      - HF_HUB_CACHE=/data
+    command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            # that's the closest analogue to --gpus; provide
+            # an integer amount of devices or 'all'
+            count: 1
+            # Devices are reserved using a list of capabilities, making
+            # capabilities the only required field. A device MUST
+            # satisfy all the requested capabilities for a successful
+            # reservation.
+            capabilities: [gpu]
+    runtime: nvidia
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://text-generation-inference:5009/health"]
+      interval: 5s
+      timeout: 5s
+      retries: 30
+  llamastack:
+    depends_on:
+      text-generation-inference:
+        condition: service_healthy
+    image: llamastack/llamastack-local-cpu
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      # Link to run.yaml file
+      - ./run.yaml:/root/my-run.yaml
+    ports:
+      - "5000:5000"
+    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
+    restart_policy:
+      condition: on-failure
+      delay: 3s
+      max_attempts: 5
+      window: 60s

distributions/tgi/cpu/run.yaml

@@ -0,0 +1,46 @@
+version: '2'
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
+apis:
+- shields
+- agents
+- models
+- memory
+- memory_banks
+- inference
+- safety
+providers:
+  inference:
+  - provider_id: tgi0
+    provider_type: remote::tgi
+    config:
+      url: <ENTER_YOUR_TGI_HOSTED_ENDPOINT>
+  safety:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
+  memory:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}
+  agents:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: ~/.llama/runtime/kvstore.db
+  telemetry:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}

distributions/tgi/gpu/compose.yaml

@@ -34,7 +34,7 @@ services:
       interval: 5s
       timeout: 5s
       retries: 30
-  llamastack-local-cpu:
+  llamastack:
     depends_on:
       text-generation-inference:
         condition: service_healthy
@@ -43,11 +43,11 @@ services:
     volumes:
       - ~/.llama:/root/.llama
       # Link to TGI run.yaml file
-      - ./tgi-run.yaml:/root/llamastack-run-tgi.yaml
+      - ./run.yaml:/root/my-run.yaml
     ports:
       - "5000:5000"
     # Hack: wait for TGI server to start before starting docker
-    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-tgi.yaml"
+    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
     restart_policy:
       condition: on-failure
       delay: 3s

llama_stack/distribution/docker/README.md

@@ -1,28 +0,0 @@
-# Docker Compose Scripts
-
-This folder contains scripts to enable starting a distribution using `docker compose`.
-
-
-#### Example: TGI Inference Adapter
-```
-$ cd llama_stack/distribution/docker/tgi
-$ ls
-compose.yaml  tgi-run.yaml
-$ docker compose up
-```
-
-The script will first start up TGI server, then start up Llama Stack distribution server hooking up to the remote TGI provider for inference. You should be able to see the following outputs --
-```
-[text-generation-inference] | 2024-10-15T18:56:33.810397Z  INFO text_generation_router::server: router/src/server.rs:1813: Using config Some(Llama)
-[text-generation-inference] | 2024-10-15T18:56:33.810448Z  WARN text_generation_router::server: router/src/server.rs:1960: Invalid hostname, defaulting to 0.0.0.0
-[text-generation-inference] | 2024-10-15T18:56:33.864143Z  INFO text_generation_router::server: router/src/server.rs:2353: Connected
-INFO:     Started server process [1]
-INFO:     Waiting for application startup.
-INFO:     Application startup complete.
-INFO:     Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
-```
-
-To kill the server
-```
-docker compose down
-```

llama_stack/distribution/templates/build_configs/local-ollama-build.yaml

@@ -3,7 +3,10 @@ distribution_spec:
   description: Like local, but use ollama for running LLM inference
   providers:
     inference: remote::ollama
-    memory: meta-reference
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
     safety: meta-reference
     agents: meta-reference
     telemetry: meta-reference