llama stack distributions / templates / docker refactor (#266)

* docker compose ollama * comment * update compose file * readme for distributions * readme * move distribution folders * move distribution/templates to distributions/ * rename * kill distribution/templates * readme * readme * build/developer cookbook/new api provider * developer cookbook * readme * readme * [bugfix] fix case for agent when memory bank registered without specifying provider_id (#264) * fix case where memory bank is registered without provider_id * memory test * agents unit test * Add an option to not use elastic agents for meta-reference inference (#269) * Allow overridding checkpoint_dir via config * Small rename * Make all methods `async def` again; add completion() for meta-reference (#270) PR #201 had made several changes while trying to fix issues with getting the stream=False branches of inference and agents API working. As part of this, it made a change which was slightly gratuitous. Namely, making chat_completion() and brethren "def" instead of "async def". The rationale was that this allowed the user (within llama-stack) of this to use it as: ``` async for chunk in api.chat_completion(params) ``` However, it causes unnecessary confusion for several folks. Given that clients (e.g., llama-stack-apps) anyway use the SDK methods (which are completely isolated) this choice was not ideal. Let's revert back so the call now looks like: ``` async for chunk in await api.chat_completion(params) ``` Bonus: Added a completion() implementation for the meta-reference provider. Technically should have been another PR :) * Improve an important error message * update ollama for llama-guard3 * Add vLLM inference provider for OpenAI compatible vLLM server (#178) This PR adds vLLM inference provider for OpenAI compatible vLLM server. * Create .readthedocs.yaml Trying out readthedocs * Update event_logger.py (#275) spelling error * vllm * build templates * delete templates * tmp add back build to avoid merge conflicts * vllm * vllm --------- Co-authored-by: Ashwin Bharambe <[email protected]> Co-authored-by: Ashwin Bharambe <[email protected]> Co-authored-by: Yuan Tang <[email protected]> Co-authored-by: raghotham <[email protected]> Co-authored-by: nehal-a2z <[email protected]>
meta-llama · Oct 21, 2024 · 23210e8 · 23210e8
1 parent c995219
commit 23210e8
Show file tree

Hide file tree

Showing 32 changed files with 850 additions and 335 deletions.
diff --git a/distributions/README.md b/distributions/README.md
@@ -0,0 +1,11 @@
+# Llama Stack Distribution
+
+A Distribution is where APIs and Providers are assembled together to provide a consistent whole to the end application developer. You can mix-and-match providers -- some could be backed by local code and some could be remote. As a hobbyist, you can serve a small model locally, but can choose a cloud provider for a large model. Regardless, the higher level APIs your app needs to work with don't need to change at all. You can even imagine moving across the server / mobile-device boundary as well always using the same uniform set of APIs for developing Generative AI applications.
+
+
+## Quick Start Llama Stack Distributions Guide
+| **Distribution** 	|           **Llama Stack Docker**           	| Start This Distribution 	|    **Inference**   	|     **Agents**     	|     **Memory**     	|     **Safety**     	|    **Telemetry**   	|
+|:----------------:	|:------------------------------------------:	|:-----------------------:	|:------------------:	|:------------------:	|:------------------:	|:------------------:	|:------------------:	|
+|  Meta Reference  	| llamastack/distribution-meta-reference-gpu 	|       [Guide](./meta-reference-gpu/)       	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	|
+|      Ollama      	|       llamastack/distribution-ollama       	|       [Guide](./ollama/)       	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	|
+|        TGI       	|         llamastack/distribution-tgi        	|       [Guide](./tgi/)       	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	| :heavy_check_mark: 	|
diff --git a/...gs/local-bedrock-conda-example-build.yaml → distributions/bedrock/build.yaml b/...gs/local-bedrock-conda-example-build.yaml → distributions/bedrock/build.yaml
@@ -1,4 +1,4 @@
-name: local-bedrock-conda-example
+name: bedrock
 distribution_spec:
   description: Use Amazon Bedrock APIs.
   providers:

diff --git a/...build_configs/local-databricks-build.yaml → distributions/databricks/build.yaml b/...build_configs/local-databricks-build.yaml → distributions/databricks/build.yaml
@@ -1,4 +1,4 @@
-name: local-databricks
+name: databricks
 distribution_spec:
   description: Use Databricks for running LLM inference
   providers:
@@ -7,4 +7,4 @@ distribution_spec:
     safety: meta-reference
     agents: meta-reference
     telemetry: meta-reference
-image_type: conda
+image_type: conda
diff --git a/.../build_configs/local-fireworks-build.yaml → distributions/fireworks/build.yaml b/.../build_configs/local-fireworks-build.yaml → distributions/fireworks/build.yaml
@@ -1,4 +1,4 @@
-name: local-fireworks
+name: fireworks
 distribution_spec:
   description: Use Fireworks.ai for running LLM inference
   providers:

diff --git a/...uild_configs/local-hf-endpoint-build.yaml → distributions/hf-endpoint/build.yaml b/...uild_configs/local-hf-endpoint-build.yaml → distributions/hf-endpoint/build.yaml
@@ -1,4 +1,4 @@
-name: local-hf-endpoint
+name: hf-endpoint
 distribution_spec:
   description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
   providers:

diff --git a/...ld_configs/local-hf-serverless-build.yaml → distributions/hf-serverless/build.yaml b/...ld_configs/local-hf-serverless-build.yaml → distributions/hf-serverless/build.yaml
@@ -1,4 +1,4 @@
-name: local-hf-serverless
+name: hf-serverless
 distribution_spec:
   description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
   providers:

diff --git a/distributions/meta-reference-gpu/README.md b/distributions/meta-reference-gpu/README.md
@@ -0,0 +1,33 @@
+# Meta Reference Distribution
+
+The `llamastack/distribution-meta-reference-gpu` distribution consists of the following provider configurations.
+
+
+| **API**         	| **Inference** 	| **Agents**     	| **Memory**                                       	| **Safety**     	| **Telemetry**  	|
+|-----------------	|---------------	|----------------	|--------------------------------------------------	|----------------	|----------------	|
+| **Provider(s)** 	| meta-reference  	| 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.
+
+> [!NOTE]
+> For GPU inference, you need to set these environment variables for specifying local directory containing your model checkpoints, and enable GPU inference to start running docker container.
+```
+export LLAMA_CHECKPOINT_DIR=~/.llama
+```
+
+> [!NOTE]
+> `~/.llama` should be the path containing downloaded weights of Llama models.
+
+
+To download and start running a pre-built docker container, you may use the following commands:
+
+```
+docker run -it -p 5000:5000 -v ~/.llama:/root/.llama --gpus=all llamastack/llamastack-local-gpu
+```
+
+### Alternative (Build and start distribution locally via conda)
+- You may checkout the [Getting Started](../../docs/getting_started.md) for more details on starting up a meta-reference distribution.
diff --git a/...build_configs/local-gpu-docker-build.yaml → distributions/meta-reference-gpu/build.yaml b/...build_configs/local-gpu-docker-build.yaml → distributions/meta-reference-gpu/build.yaml
@@ -1,9 +1,12 @@
-name: local-gpu
+name: distribution-meta-reference-gpu
 distribution_spec:
   description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
     inference: meta-reference
-    memory: meta-reference
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
     safety: meta-reference
     agents: meta-reference
     telemetry: meta-reference

diff --git a/...tion/templates/run_configs/local-run.yaml → distributions/meta-reference-gpu/run.yaml b/...tion/templates/run_configs/local-run.yaml → distributions/meta-reference-gpu/run.yaml
@@ -13,7 +13,7 @@ apis:
 - safety
 providers:
   inference:
-  - provider_id: meta-reference
+  - provider_id: meta0
     provider_type: meta-reference
     config:
       model: Llama3.1-8B-Instruct
@@ -22,7 +22,7 @@ providers:
       max_seq_len: 4096
       max_batch_size: 1
   safety:
-  - provider_id: meta-reference
+  - provider_id: meta0
     provider_type: meta-reference
     config:
       llama_guard_shield:
@@ -33,18 +33,18 @@ providers:
       prompt_guard_shield:
         model: Prompt-Guard-86M
   memory:
-  - provider_id: meta-reference
+  - provider_id: meta0
     provider_type: meta-reference
     config: {}
   agents:
-  - provider_id: meta-reference
+  - provider_id: meta0
     provider_type: meta-reference
     config:
       persistence_store:
         namespace: null
         type: sqlite
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
-  - provider_id: meta-reference
+  - provider_id: meta0
     provider_type: meta-reference
     config: {}
diff --git a/distributions/ollama/README.md b/distributions/ollama/README.md
@@ -0,0 +1,91 @@
+# Ollama Distribution
+
+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.
+
+```
+$ cd llama-stack/distribution/ollama/gpu
+$ ls
+compose.yaml  run.yaml
+$ docker compose up
+```
+
+You will see outputs similar to following ---
+```
+[ollama]               | [GIN] 2024/10/18 - 21:19:41 | 200 |     226.841µs |             ::1 | GET      "/api/ps"
+[ollama]               | [GIN] 2024/10/18 - 21:19:42 | 200 |      60.908µs |             ::1 | GET      "/api/ps"
+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] | Resolved 12 providers
+[llamastack] |  inner-inference => ollama0
+[llamastack] |  models => __routing_table__
+[llamastack] |  inference => __autorouted__
+```
+
+To kill the server
+```
+docker compose down
+```
+
+### 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.
+- Please check the [Ollama Documentations](https://github.com/ollama/ollama) for more details.
+
+**Via Docker**
+```
+docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
+```
+
+**Via CLI**
+```
+ollama run <model_id>
+```
+
+#### 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
+```
+
+Make sure in you `ollama-run.yaml` file, you inference provider is pointing to the correct Ollama endpoint. E.g.
+```
+inference:
+  - provider_id: ollama0
+    provider_type: remote::ollama
+    config:
+      url: http://127.0.0.1:14343
+```
+
+**Via Conda**
+
+```
+llama stack build --config ./build.yaml
+llama stack run ./gpu/run.yaml
+```
diff --git a/distributions/ollama/build.yaml b/distributions/ollama/build.yaml
@@ -0,0 +1,13 @@
+name: distribution-ollama
+distribution_spec:
+  description: 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
diff --git a/distributions/ollama/cpu/compose.yaml b/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:
diff --git a/distributions/ollama/cpu/run.yaml b/distributions/ollama/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: 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: {}
diff --git a/distributions/ollama/gpu/compose.yaml b/distributions/ollama/gpu/compose.yaml
@@ -0,0 +1,48 @@
+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"
+    devices:
+      - nvidia.com/gpu=all
+    environment:
+      - CUDA_VISIBLE_DEVICES=0
+    command: []
+    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
+  llamastack-local-cpu:
+    depends_on:
+    - ollama
+    image: llamastack/llamastack-local-cpu
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      # Link to ollama run.yaml file
+      - ./ollama-run.yaml:/root/llamastack-run-ollama.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/llamastack-run-ollama.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
+volumes:
+  ollama: