fix(client): include openllm.client into main module [skip ci]

Signed-off-by: Aaron <[email protected]>

Author: aarnphm

.github/workflows/build.yml

@@ -13,7 +13,6 @@ on:
       - ".github/workflows/build.yaml"
       - "src/openllm/bundle/oci/Dockerfile"
       - "src/openllm/**"
-      - "src/openllm_client/**"
 env:
   LINES: 120
   COLUMNS: 120

DEVELOPMENT.md

@@ -74,7 +74,6 @@ openllm/
 ├── examples                 # Usage demonstration scripts
 ├── src
 │   ├── openllm              # openllm core
-│   ├── openllm_client       # openllm python client
 │   └── openllm-node         # openllm nodejs library
 ├── tests                    # Automated Tests
 ├── tools                    # Utilities Script

pyproject.toml

@@ -284,7 +284,7 @@ avoid-escape = false
 "src/openllm/models/**" = ["I001", "E", "D", "F"]
 "src/openllm/utils/__init__.py" = ["I001"]
 "src/openllm/utils/import_utils.py" = ["PLW0603"]
-"src/openllm_client/runtimes/*" = ["D107"]
+"src/openllm/client/runtimes/*" = ["D107"]
 "tests/**/*" = [
     "S101",
     "TID252",
@@ -395,7 +395,7 @@ exclude = [
     "examples",
     "tests",
 ]
-include = ["src/openllm", "src/openllm_client"]
+include = ["src/openllm"]
 pythonVersion = "3.12"
 reportMissingImports = "warning"
 reportMissingTypeStubs = false
@@ -411,7 +411,7 @@ typeCheckingMode = "strict"
 # TODO: Enable model for strict type checking
 exclude = ["src/openllm/playground/", "src/openllm/utils/dummy_*.py", "src/openllm/models"]
 local_partial_types = true
-modules = ["openllm", "openllm_client"]
+modules = ["openllm"]
 mypy_path = "typings"
 pretty = true
 python_version = "3.11"
@@ -500,7 +500,6 @@ include = [
     "src/openllm/_quantisation.py",
     "src/openllm/_generation.py",
     "src/openllm/_strategies.py",
-    "src/openllm/client.py",
     "src/openllm/exceptions.py",
     "src/openllm/testing.py",
 ]

src/openllm/cli/entrypoint.py

@@ -69,11 +69,7 @@
   start_command_factory,
   workers_per_resource_option,
 )
-from .. import (
-  bundle,
-  client as openllm_client,
-  serialisation,
-)
+from .. import bundle, serialisation
 from ..exceptions import OpenLLMException
 from ..models.auto import (
   CONFIG_MAPPING,
@@ -109,10 +105,10 @@
 
 if t.TYPE_CHECKING:
   import torch
-  from openllm_client.runtimes.base import BaseClient
 
   from bentoml._internal.bento import BentoStore
   from bentoml._internal.container import DefaultBuilder
+  from openllm.client import BaseClient
 
   from .._schema import EmbeddingsOutput
   from .._types import DictStrAny, LiteralRuntime, P
@@ -713,7 +709,7 @@ def instruct_command(endpoint: str, timeout: int, agent: t.LiteralString, output
         --text "¡Este es un API muy agradable!"
   ```
   """
-  client = openllm_client.HTTPClient(endpoint, timeout=timeout)
+  client = openllm.client.HTTPClient(endpoint, timeout=timeout)
 
   try:
     client.call("metadata")
@@ -745,7 +741,7 @@ def embed_command(ctx: click.Context, text: tuple[str, ...], endpoint: str, time
   $ openllm embed --endpoint http://12.323.2.1:3000 "What is the meaning of life?" "How many stars are there in the sky?"
   ```
   """
-  client = t.cast("BaseClient[t.Any]", openllm_client.HTTPClient(endpoint, timeout=timeout) if server_type == "http" else openllm_client.GrpcClient(endpoint, timeout=timeout))
+  client = t.cast("BaseClient[t.Any]", openllm.client.HTTPClient(endpoint, timeout=timeout) if server_type == "http" else openllm.client.GrpcClient(endpoint, timeout=timeout))
   try:
     gen_embed = client.embed(text)
   except ValueError:
@@ -778,7 +774,7 @@ def query_command(ctx: click.Context, /, prompt: str, endpoint: str, timeout: in
   """
   _memoized = {k: orjson.loads(v[0]) for k, v in _memoized.items() if v}
   if server_type == "grpc": endpoint = re.sub(r"http://", "", endpoint)
-  client = t.cast("BaseClient[t.Any]", openllm_client.HTTPClient(endpoint, timeout=timeout) if server_type == "http" else openllm_client.GrpcClient(endpoint, timeout=timeout))
+  client = t.cast("BaseClient[t.Any]", openllm.client.HTTPClient(endpoint, timeout=timeout) if server_type == "http" else openllm.client.GrpcClient(endpoint, timeout=timeout))
   input_fg, generated_fg = "magenta", "cyan"
   if output != "porcelain":
     termui.echo("==Input==\n", fg="white")

src/openllm/client.py

@@ -6,11 +6,11 @@
 """
 from __future__ import annotations
 
-from .runtimes.grpc import (
+from .runtimes import (
     AsyncGrpcClient as AsyncGrpcClient,
-    GrpcClient as GrpcClient,
-)
-from .runtimes.http import (
     AsyncHTTPClient as AsyncHTTPClient,
+    BaseAsyncClient as BaseAsyncClient,
+    BaseClient as BaseClient,
+    GrpcClient as GrpcClient,
     HTTPClient as HTTPClient,
 )

src/openllm_client/__init__.py renamed to src/openllm/client/__init__.py

@@ -1,4 +1,3 @@
-
 from __future__ import annotations
 import asyncio
 import logging

src/openllm_client/runtimes/__init__.py renamed to src/openllm/client/runtimes/__init__.py

@@ -1,4 +1,3 @@
-
 from __future__ import annotations
 import logging
 import typing as t