Some more toolchain -> stack changes

llama_stack/cli/stack/configure.py

@@ -107,7 +107,7 @@ class StackConfigure(Subcommand):
 
         if run_config_file.exists():
             cprint(
-                f"Configuration already exists for {build_config.name}. Will overwrite...",
+                f"Configuration already exists at `{str(run_config_file)}`. Will overwrite...",
                 "yellow",
                 attrs=["bold"],
             )

llama_stack/configs/distributions/conda/local-conda-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
     inference: meta-reference
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: conda

llama_stack/configs/distributions/conda/local-fireworks-conda-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Use Fireworks.ai for running LLM inference
   providers:
     inference: remote::fireworks
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: conda

llama_stack/configs/distributions/conda/local-ollama-conda-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Like local, but use ollama for running LLM inference
   providers:
     inference: remote::ollama
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: conda

llama_stack/configs/distributions/conda/local-tgi-conda-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Use TGI (local or with Hugging Face Inference Endpoints for running LLM inference. When using HF Inference Endpoints, you must provide the name of the endpoint).
   providers:
     inference: remote::tgi
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: conda

llama_stack/configs/distributions/conda/local-together-conda-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Use Together.ai for running LLM inference
   providers:
     inference: remote::together
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: conda

llama_stack/configs/distributions/docker/local-docker-example-build.yaml

@@ -3,8 +3,8 @@ distribution_spec:
   description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
     inference: meta-reference
-    memory: meta-reference-faiss
+    memory: meta-reference
     safety: meta-reference
     agents: meta-reference
-    telemetry: console
+    telemetry: meta-reference
 image_type: docker

llama_stack/distribution/build_conda_env.sh

@@ -7,11 +7,11 @@
 # the root directory of this source tree.
 
 LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
-LLAMA_TOOLCHAIN_DIR=${LLAMA_TOOLCHAIN_DIR:-}
+LLAMA_STACK_DIR=${LLAMA_STACK_DIR:-}
 TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
 
-if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
+if [ -n "$LLAMA_STACK_DIR" ]; then
-  echo "Using llama-stack-dir=$LLAMA_TOOLCHAIN_DIR"
+  echo "Using llama-stack-dir=$LLAMA_STACK_DIR"
 fi
 if [ -n "$LLAMA_MODELS_DIR" ]; then
   echo "Using llama-models-dir=$LLAMA_MODELS_DIR"
@@ -81,14 +81,14 @@ ensure_conda_env_python310() {
     pip install --extra-index-url https://test.pypi.org/simple/ llama-models==$TEST_PYPI_VERSION llama-stack==$TEST_PYPI_VERSION $pip_dependencies
   else
     # Re-installing llama-stack in the new conda environment
-    if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
+    if [ -n "$LLAMA_STACK_DIR" ]; then
-      if [ ! -d "$LLAMA_TOOLCHAIN_DIR" ]; then
+      if [ ! -d "$LLAMA_STACK_DIR" ]; then
-        printf "${RED}Warning: LLAMA_TOOLCHAIN_DIR is set but directory does not exist: $LLAMA_TOOLCHAIN_DIR${NC}\n" >&2
+        printf "${RED}Warning: LLAMA_STACK_DIR is set but directory does not exist: $LLAMA_STACK_DIR${NC}\n" >&2
         exit 1
       fi
 
-      printf "Installing from LLAMA_TOOLCHAIN_DIR: $LLAMA_TOOLCHAIN_DIR\n"
+      printf "Installing from LLAMA_STACK_DIR: $LLAMA_STACK_DIR\n"
-      pip install --no-cache-dir -e "$LLAMA_TOOLCHAIN_DIR"
+      pip install --no-cache-dir -e "$LLAMA_STACK_DIR"
     else
       pip install --no-cache-dir llama-stack
     fi

llama_stack/distribution/build_container.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
-LLAMA_TOOLCHAIN_DIR=${LLAMA_TOOLCHAIN_DIR:-}
+LLAMA_STACK_DIR=${LLAMA_STACK_DIR:-}
 TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
 
 if [ "$#" -ne 4 ]; then
@@ -55,15 +55,15 @@ RUN apt-get update && apt-get install -y \
 
 EOF
 
-toolchain_mount="/app/llama-stack-source"
+stack_mount="/app/llama-stack-source"
 models_mount="/app/llama-models-source"
 
-if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
+if [ -n "$LLAMA_STACK_DIR" ]; then
-  if [ ! -d "$LLAMA_TOOLCHAIN_DIR" ]; then
+  if [ ! -d "$LLAMA_STACK_DIR" ]; then
-    echo "${RED}Warning: LLAMA_TOOLCHAIN_DIR is set but directory does not exist: $LLAMA_TOOLCHAIN_DIR${NC}" >&2
+    echo "${RED}Warning: LLAMA_STACK_DIR is set but directory does not exist: $LLAMA_STACK_DIR${NC}" >&2
     exit 1
   fi
-  add_to_docker "RUN pip install $toolchain_mount"
+  add_to_docker "RUN pip install $stack_mount"
 else
   add_to_docker "RUN pip install llama-stack"
 fi
@@ -90,7 +90,7 @@ add_to_docker <<EOF
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway
 #
-# ENTRYPOINT ["python", "-m", "llama_stack.distribution.server"]
+# ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
 
 EOF
 
@@ -101,8 +101,8 @@ cat $TEMP_DIR/Dockerfile
 printf "\n"
 
 mounts=""
-if [ -n "$LLAMA_TOOLCHAIN_DIR" ]; then
+if [ -n "$LLAMA_STACK_DIR" ]; then
-  mounts="$mounts -v $(readlink -f $LLAMA_TOOLCHAIN_DIR):$toolchain_mount"
+  mounts="$mounts -v $(readlink -f $LLAMA_STACK_DIR):$stack_mount"
 fi
 if [ -n "$LLAMA_MODELS_DIR" ]; then
   mounts="$mounts -v $(readlink -f $LLAMA_MODELS_DIR):$models_mount"

llama_stack/distribution/configure.py

@@ -81,11 +81,13 @@ def configure_api_providers(
                 )
             config.provider_map[api_str] = routing_entries
         else:
-            provider_spec = all_providers[api][spec.providers[api_str]]
+            p = spec.providers[api_str]
+            print(f"Configuring provider `{p}`...")
+            provider_spec = all_providers[api][p]
             config_type = instantiate_class_type(provider_spec.config_class)
             cfg = prompt_for_config(config_type, None)
             config.provider_map[api_str] = GenericProviderConfig(
-                provider_id=spec.providers[api_str],
+                provider_id=p,
                 config=cfg.dict(),
             )
 

llama_stack/distribution/server/__init__.py

@@ -3,10 +3,3 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-
-import fire
-
-from .server import main
-
-if __name__ == __main__:
-    fire.Fire(main)

llama_stack/distribution/server/server.py

@@ -47,8 +47,8 @@ from llama_stack.providers.utils.telemetry.tracing import (
 )
 from llama_stack.distribution.datatypes import *  # noqa: F403
 
-from .distribution import api_endpoints, api_providers
+from llama_stack.distribution.distribution import api_endpoints, api_providers
-from .dynamic import instantiate_provider
+from llama_stack.distribution.utils.dynamic import instantiate_provider
 
 
 def is_async_iterator_type(typ):

llama_stack/distribution/start_conda_env.sh

@@ -37,6 +37,6 @@ eval "$(conda shell.bash hook)"
 conda deactivate && conda activate "$env_name"
 
 $CONDA_PREFIX/bin/python \
-  -m llama_stack.distribution.server \
+  -m llama_stack.distribution.server.server \
   --yaml_config "$yaml_config" \
   --port "$port" "$@"

llama_stack/distribution/start_container.sh

@@ -38,6 +38,6 @@ podman run -it \
   -p $port:$port \
   -v "$yaml_config:/app/config.yaml" \
   $docker_image \
-  python -m llama_stack.distribution.server \
+  python -m llama_stack.distribution.server.server \
   --yaml_config /app/config.yaml \
   --port $port "$@"