API Updates (#73)

* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

llama_stack/providers/impls/meta_reference/agents/rag/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.

llama_stack/providers/impls/meta_reference/agents/rag/context_retriever.py

@@ -0,0 +1,76 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import List
+
+from jinja2 import Template
+from llama_models.llama3.api import *  # noqa: F403
+
+
+from llama_stack.apis.agents import (
+    DefaultMemoryQueryGeneratorConfig,
+    LLMMemoryQueryGeneratorConfig,
+    MemoryQueryGenerator,
+    MemoryQueryGeneratorConfig,
+)
+from termcolor import cprint  # noqa: F401
+from llama_stack.apis.inference import *  # noqa: F403
+
+
+async def generate_rag_query(
+    config: MemoryQueryGeneratorConfig,
+    messages: List[Message],
+    **kwargs,
+):
+    """
+    Generates a query that will be used for
+    retrieving relevant information from the memory bank.
+    """
+    if config.type == MemoryQueryGenerator.default.value:
+        query = await default_rag_query_generator(config, messages, **kwargs)
+    elif config.type == MemoryQueryGenerator.llm.value:
+        query = await llm_rag_query_generator(config, messages, **kwargs)
+    else:
+        raise NotImplementedError(f"Unsupported memory query generator {config.type}")
+    # cprint(f"Generated query >>>: {query}", color="green")
+    return query
+
+
+async def default_rag_query_generator(
+    config: DefaultMemoryQueryGeneratorConfig,
+    messages: List[Message],
+    **kwargs,
+):
+    return config.sep.join(interleaved_text_media_as_str(m.content) for m in messages)
+
+
+async def llm_rag_query_generator(
+    config: LLMMemoryQueryGeneratorConfig,
+    messages: List[Message],
+    **kwargs,
+):
+    assert "inference_api" in kwargs, "LLMRAGQueryGenerator needs inference_api"
+    inference_api = kwargs["inference_api"]
+
+    m_dict = {"messages": [m.model_dump() for m in messages]}
+
+    template = Template(config.template)
+    content = template.render(m_dict)
+
+    model = config.model
+    message = UserMessage(content=content)
+    response = inference_api.chat_completion(
+        ChatCompletionRequest(
+            model=model,
+            messages=[message],
+            stream=False,
+        )
+    )
+
+    async for chunk in response:
+        query = chunk.completion_message.content
+
+    return query