forked from phoenix-oss/llama-stack-mirror
* add tools to chat completion request * use templates for generating system prompts * Moved ToolPromptFormat and jinja templates to llama_models.llama3.api * <WIP> memory changes - inlined AgenticSystemInstanceConfig so API feels more ergonomic - renamed it to AgentConfig, AgentInstance -> Agent - added a MemoryConfig and `memory` parameter - added `attachments` to input and `output_attachments` to the response - some naming changes * InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool * flesh out memory banks API * agentic loop has a RAG implementation * faiss provider implementation * memory client works * re-work tool definitions, fix FastAPI issues, fix tool regressions * fix agentic_system utils * basic RAG seems to work * small bug fixes for inline attachments * Refactor custom tool execution utilities * Bug fix, show memory retrieval steps in EventLogger * No need for api_key for Remote providers * add special unicode character ↵ to showcase newlines in model prompt templates * remove api.endpoints imports * combine datatypes.py and endpoints.py into api.py * Attachment / add TTL api * split batch_inference from inference * minor import fixes * use a single impl for ChatFormat.decode_assistant_mesage * use interleaved_text_media_as_str() utilityt * Fix api.datatypes imports * Add blobfile for tiktoken * Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly * templates take optional --format={json,function_tag} * Rag Updates * Add `api build` subcommand -- WIP * fix * build + run image seems to work * <WIP> adapters * bunch more work to make adapters work * api build works for conda now * ollama remote adapter works * Several smaller fixes to make adapters work Also, reorganized the pattern of __init__ inside providers so configuration can stay lightweight * llama distribution -> llama stack + containers (WIP) * All the new CLI for api + stack work * Make Fireworks and Together into the Adapter format * Some quick fixes to the CLI behavior to make it consistent * Updated README phew * Update cli_reference.md * llama_toolchain/distribution -> llama_toolchain/core * Add termcolor * update paths * Add a log just for consistency * chmod +x scripts * Fix api dependencies not getting added to configuration * missing import lol * Delete utils.py; move to agentic system * Support downloading of URLs for attachments for code interpreter * Simplify and generalize `llama api build` yay * Update `llama stack configure` to be very simple also * Fix stack start * Allow building an "adhoc" distribution * Remote `llama api []` subcommands * Fixes to llama stack commands and update docs * Update documentation again and add error messages to llama stack start * llama stack start -> llama stack run * Change name of build for less confusion * Add pyopenapi fork to the repository, update RFC assets * Remove conflicting annotation * Added a "--raw" option for model template printing --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com> Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com>
157 lines
4.2 KiB
Python
157 lines
4.2 KiB
Python
# 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.
|
|
# 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, Optional, Protocol
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel, Field
|
|
from typing_extensions import Annotated
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
|
|
|
|
@json_schema_type
|
|
class MemoryBankDocument(BaseModel):
|
|
document_id: str
|
|
content: InterleavedTextMedia | URL
|
|
mime_type: str
|
|
metadata: Dict[str, Any] = Field(default_factory=dict)
|
|
|
|
|
|
@json_schema_type
|
|
class MemoryBankType(Enum):
|
|
vector = "vector"
|
|
keyvalue = "keyvalue"
|
|
keyword = "keyword"
|
|
graph = "graph"
|
|
|
|
|
|
class VectorMemoryBankConfig(BaseModel):
|
|
type: Literal[MemoryBankType.vector.value] = MemoryBankType.vector.value
|
|
embedding_model: str
|
|
chunk_size_in_tokens: int
|
|
overlap_size_in_tokens: Optional[int] = None
|
|
|
|
|
|
class KeyValueMemoryBankConfig(BaseModel):
|
|
type: Literal[MemoryBankType.keyvalue.value] = MemoryBankType.keyvalue.value
|
|
|
|
|
|
class KeywordMemoryBankConfig(BaseModel):
|
|
type: Literal[MemoryBankType.keyword.value] = MemoryBankType.keyword.value
|
|
|
|
|
|
class GraphMemoryBankConfig(BaseModel):
|
|
type: Literal[MemoryBankType.graph.value] = MemoryBankType.graph.value
|
|
|
|
|
|
MemoryBankConfig = Annotated[
|
|
Union[
|
|
VectorMemoryBankConfig,
|
|
KeyValueMemoryBankConfig,
|
|
KeywordMemoryBankConfig,
|
|
GraphMemoryBankConfig,
|
|
],
|
|
Field(discriminator="type"),
|
|
]
|
|
|
|
|
|
class Chunk(BaseModel):
|
|
content: InterleavedTextMedia
|
|
token_count: int
|
|
document_id: str
|
|
|
|
|
|
@json_schema_type
|
|
class QueryDocumentsResponse(BaseModel):
|
|
chunks: List[Chunk]
|
|
scores: List[float]
|
|
|
|
|
|
@json_schema_type
|
|
class QueryAPI(Protocol):
|
|
@webmethod(route="/query_documents")
|
|
def query_documents(
|
|
self,
|
|
query: InterleavedTextMedia,
|
|
params: Optional[Dict[str, Any]] = None,
|
|
) -> QueryDocumentsResponse: ...
|
|
|
|
|
|
@json_schema_type
|
|
class MemoryBank(BaseModel):
|
|
bank_id: str
|
|
name: str
|
|
config: MemoryBankConfig
|
|
# if there's a pre-existing (reachable-from-distribution) store which supports QueryAPI
|
|
url: Optional[URL] = None
|
|
|
|
|
|
class Memory(Protocol):
|
|
@webmethod(route="/memory_banks/create")
|
|
async def create_memory_bank(
|
|
self,
|
|
name: str,
|
|
config: MemoryBankConfig,
|
|
url: Optional[URL] = None,
|
|
) -> MemoryBank: ...
|
|
|
|
@webmethod(route="/memory_banks/list", method="GET")
|
|
async def list_memory_banks(self) -> List[MemoryBank]: ...
|
|
|
|
@webmethod(route="/memory_banks/get", method="GET")
|
|
async def get_memory_bank(self, bank_id: str) -> Optional[MemoryBank]: ...
|
|
|
|
@webmethod(route="/memory_banks/drop", method="DELETE")
|
|
async def drop_memory_bank(
|
|
self,
|
|
bank_id: str,
|
|
) -> str: ...
|
|
|
|
# this will just block now until documents are inserted, but it should
|
|
# probably return a Job instance which can be polled for completion
|
|
@webmethod(route="/memory_bank/insert")
|
|
async def insert_documents(
|
|
self,
|
|
bank_id: str,
|
|
documents: List[MemoryBankDocument],
|
|
ttl_seconds: Optional[int] = None,
|
|
) -> None: ...
|
|
|
|
@webmethod(route="/memory_bank/update")
|
|
async def update_documents(
|
|
self,
|
|
bank_id: str,
|
|
documents: List[MemoryBankDocument],
|
|
) -> None: ...
|
|
|
|
@webmethod(route="/memory_bank/query")
|
|
async def query_documents(
|
|
self,
|
|
bank_id: str,
|
|
query: InterleavedTextMedia,
|
|
params: Optional[Dict[str, Any]] = None,
|
|
) -> QueryDocumentsResponse: ...
|
|
|
|
@webmethod(route="/memory_bank/documents/get", method="GET")
|
|
async def get_documents(
|
|
self,
|
|
bank_id: str,
|
|
document_ids: List[str],
|
|
) -> List[MemoryBankDocument]: ...
|
|
|
|
@webmethod(route="/memory_bank/documents/delete", method="DELETE")
|
|
async def delete_documents(
|
|
self,
|
|
bank_id: str,
|
|
document_ids: List[str],
|
|
) -> None: ...
|