Merge remote-tracking branch 'upstream/main' into qdrant

.gitignore

@@ -14,3 +14,4 @@ Package.resolved
 *.pte
 *.ipynb_checkpoints*
 .venv/
+.idea

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Contributing to Llama-Models
+# Contributing to Llama-Stack
 We want to make contributing to this project as easy and transparent as
 possible.
 
@@ -32,7 +32,7 @@ outlined on that page and do not file a public issue.
 * ...
 
 ## Tips
-* If you are developing with a llama-models repository checked out and need your distribution to reflect changes from there, set `LLAMA_MODELS_DIR` to that dir when running any of the `llama` CLI commands.
+* If you are developing with a llama-stack repository checked out and need your distribution to reflect changes from there, set `LLAMA_STACK_DIR` to that dir when running any of the `llama` CLI commands.
 
 ## License
 By contributing to Llama, you agree that your contributions will be licensed

README.md

@@ -81,11 +81,24 @@ cd llama-stack
 $CONDA_PREFIX/bin/pip install -e .
 ```
 
-## The Llama CLI
+## Documentations
 
-The `llama` CLI makes it easy to work with the Llama Stack set of tools, including installing and running Distributions, downloading models, studying model prompt formats, etc. Please see the [CLI reference](docs/cli_reference.md) for details. Please see the [Getting Started](docs/getting_started.md) guide for running a Llama Stack server.
+The `llama` CLI makes it easy to work with the Llama Stack set of tools. Please find the following docs for details.
+
+* [CLI reference](docs/cli_reference.md)
+    * Guide using `llama` CLI to work with Llama models (download, study prompts), and building/starting a Llama Stack distribution.
+* [Getting Started](docs/getting_started.md)
+    * Guide to build and run a Llama Stack server.
+* [Contributing](CONTRIBUTING.md)
 
 
 ## Llama Stack Client SDK
 
+|  **Language** |  **Client SDK** | **Package** |
+| :----: | :----: | :----: |
+| Python |  [llama-stack-client-python](https://github.com/meta-llama/llama-stack-client-python) | [![PyPI version](https://img.shields.io/pypi/v/llama_stack_client.svg)](https://pypi.org/project/llama_stack_client/)
+| Swift  | [llama-stack-client-swift](https://github.com/meta-llama/llama-stack-client-swift) |
+| Node   | [llama-stack-client-node](https://github.com/meta-llama/llama-stack-client-node) | [![NPM version](https://img.shields.io/npm/v/llama-stack-client.svg)](https://npmjs.org/package/llama-stack-client)
+| Kotlin | [llama-stack-client-kotlin](https://github.com/meta-llama/llama-stack-client-kotlin) |
+
 Check out our client SDKs for connecting to Llama Stack server in your preferred language, you can choose from [python](https://github.com/meta-llama/llama-stack-client-python), [node](https://github.com/meta-llama/llama-stack-client-node), [swift](https://github.com/meta-llama/llama-stack-client-swift), and [kotlin](https://github.com/meta-llama/llama-stack-client-kotlin) programming languages to quickly build your applications.

SECURITY.md

@@ -0,0 +1,5 @@
+# Security Policy
+
+## Reporting a Vulnerability
+
+Please report vulnerabilities to our bug bounty program at https://bugbounty.meta.com/

docs/cli_reference.md

@@ -1,6 +1,6 @@
 # Llama CLI Reference
 
-The `llama` CLI tool helps you setup and use the Llama toolchain & agentic systems. It should be available on your path after installing the `llama-stack` package.
+The `llama` CLI tool helps you setup and use the Llama Stack & agentic systems. It should be available on your path after installing the `llama-stack` package.
 
 ### Subcommands
 1. `download`: `llama` cli tools supports downloading the model from Meta or Hugging Face.

llama_stack/apis/inference/client.py

@@ -6,7 +6,6 @@
 
 import asyncio
 import json
-import sys
 from typing import Any, AsyncGenerator, List, Optional
 
 import fire
@@ -101,7 +100,9 @@ class InferenceClient(Inference):
                             print(f"Error with parsing or validation: {e}")
 
 
-async def run_main(host: str, port: int, stream: bool, model: Optional[str]):
+async def run_main(
+    host: str, port: int, stream: bool, model: Optional[str], logprobs: bool
+):
     client = InferenceClient(f"http://{host}:{port}")
 
     if not model:
@@ -111,11 +112,25 @@ async def run_main(host: str, port: int, stream: bool, model: Optional[str]):
         content="hello world, write me a 2 sentence poem about the moon"
     )
     cprint(f"User>{message.content}", "green")
+
+    if logprobs:
+        logprobs_config = LogProbConfig(
+            top_k=1,
+        )
+    else:
+        logprobs_config = None
+
     iterator = client.chat_completion(
         model=model,
         messages=[message],
         stream=stream,
+        logprobs=logprobs_config,
     )
+
+    if logprobs:
+        async for chunk in iterator:
+            cprint(f"Response: {chunk}", "red")
+    else:
         async for log in EventLogger().log(iterator):
             log.print()
 
@@ -149,13 +164,14 @@ def main(
     port: int,
     stream: bool = True,
     mm: bool = False,
+    logprobs: bool = False,
     file: Optional[str] = None,
     model: Optional[str] = None,
 ):
     if mm:
         asyncio.run(run_mm_main(host, port, stream, file, model))
     else:
-        asyncio.run(run_main(host, port, stream, model))
+        asyncio.run(run_main(host, port, stream, model, logprobs))
 
 
 if __name__ == "__main__":

llama_stack/cli/download.py

@@ -169,7 +169,7 @@ def run_download_cmd(args: argparse.Namespace, parser: argparse.ArgumentParser):
         meta_url = args.meta_url
         if not meta_url:
             meta_url = input(
-                "Please provide the signed URL you received via email (e.g., https://llama3-1.llamameta.net/*?Policy...): "
+                "Please provide the signed URL you received via email after visiting https://www.llama.com/llama-downloads/ (e.g., https://llama3-1.llamameta.net/*?Policy...): "
             )
             assert meta_url is not None and "llamameta.net" in meta_url
         _meta_download(model, meta_url, info)

llama_stack/providers/impls/meta_reference/agents/agent_instance.py

@@ -673,7 +673,7 @@ class ChatAgent(ShieldRunnerMixin):
 
     async def _retrieve_context(
         self, session_id: str, messages: List[Message], attachments: List[Attachment]
-    ) -> Tuple[List[str], List[int]]:  # (rag_context, bank_ids)
+    ) -> Tuple[Optional[List[str]], Optional[List[int]]]:  # (rag_context, bank_ids)
         bank_ids = []
 
         memory = self._memory_tool_definition()
@@ -722,12 +722,13 @@ class ChatAgent(ShieldRunnerMixin):
         chunks = [c for r in results for c in r.chunks]
         scores = [s for r in results for s in r.scores]
 
+        if not chunks:
+            return None, bank_ids
+
         # sort by score
         chunks, scores = zip(
             *sorted(zip(chunks, scores), key=lambda x: x[1], reverse=True)
         )
-        if not chunks:
-            return None, bank_ids
 
         tokens = 0
         picked = []

llama_stack/providers/impls/meta_reference/inference/generation.py

@@ -297,7 +297,7 @@ class Llama:
                 token=next_token[0].item(),
                 text=self.tokenizer.decode(next_token.tolist()),
                 logprobs=(
-                    token_logprobs[:, prev_pos + 1 : cur_pos + 1][0].tolist()
+                    token_logprobs[:, cur_pos : cur_pos + 1][0].tolist()
                     if logprobs
                     else None
                 ),

llama_stack/providers/impls/meta_reference/inference/inference.py

@@ -132,7 +132,20 @@ class MetaReferenceInferenceImpl(Inference, RoutableProvider):
 
                 if not request.stream:
                     if request.logprobs:
-                        logprobs.append(token_result.logprob)
+                        assert (
+                            len(token_result.logprobs) == 1
+                        ), "Expected logprob to contain 1 result for the current token"
+                        assert (
+                            request.logprobs.top_k == 1
+                        ), "Only top_k=1 is supported for LogProbConfig"
+
+                        logprobs.append(
+                            TokenLogProbs(
+                                logprobs_by_token={
+                                    token_result.text: token_result.logprobs[0]
+                                }
+                            )
+                        )
 
                     continue
 

llama_stack/providers/registry/memory.py

@@ -59,7 +59,7 @@ def available_providers() -> List[ProviderSpec]:
         remote_provider_spec(
             Api.memory,
             AdapterSpec(
-                adapter_id="weaviate",
+                adapter_type="weaviate",
                 pip_packages=EMBEDDING_DEPS + ["weaviate-client"],
                 module="llama_stack.providers.adapters.memory.weaviate",
                 provider_data_validator="llama_stack.providers.adapters.memory.weaviate.WeaviateRequestProviderData",

setup.py

@@ -30,7 +30,16 @@ setup(
     long_description_content_type="text/markdown",
     url="https://github.com/meta-llama/llama-stack",
     packages=find_packages(),
-    classifiers=[],
+    classifiers=[
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3",
+        "Operating System :: OS Independent",
+        "Intended Audience :: Developers",
+        "Intended Audience :: Information Technology",
+        "Intended Audience :: Science/Research",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "Topic :: Scientific/Engineering :: Information Analysis",
+    ],
     python_requires=">=3.10",
     install_requires=read_requirements(),
     include_package_data=True,