seekrai 0.0.1__py3-none-any.whl → 0.1.1__py3-none-any.whl

seekrai/types/models.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from enum import Enum
-from typing import Literal
+from typing import List, Literal
 
 from seekrai.types.abstract import BaseModel
 from seekrai.types.common import ObjectType
@@ -10,21 +10,20 @@ from seekrai.types.common import ObjectType
 class ModelType(str, Enum):
     CHAT = "chat"
     LANGUAGE = "language"
-    CODE = "code"
-    IMAGE = "image"
     EMBEDDING = "embedding"
-    MODERATION = "moderation"
+    OBJECT_DETECTION = "object_detection"
+    IMAGE_CLASSIFICATION = "image_classification"
 
 
-class PricingObject(BaseModel):
-    input: float | None = None
-    output: float | None = None
-    hourly: float | None = None
-    base: float | None = None
-    finetune: float | None = None
+# class PricingObject(BaseModel):
+#     input: float | None = None
+#     output: float | None = None
+#     hourly: float | None = None
+#     base: float | None = None
+#     finetune: float | None = None
 
 
-class ModelObject(BaseModel):
+class ModelResponse(BaseModel):
     # model id
     id: str
     # object type
@@ -32,12 +31,19 @@ class ModelObject(BaseModel):
     created: int | None = None
     # model type
     type: ModelType | None = None
-    # pretty name
-    display_name: str | None = None
-    # model creator organization
-    organization: str | None = None
-    # link to model resource
-    link: str | None = None
-    license: str | None = None
-    context_length: int | None = None
-    pricing: PricingObject
+    name: str | None = None
+    bytes: int | None = None
+    # # model creator organization
+    # organization: str | None = None
+    # # link to model resource
+    # link: str | None = None
+    # license: str | None = None
+    # context_length: int | None = None
+    # pricing: PricingObject
+
+
+class ModelList(BaseModel):
+    # object type
+    object: Literal["list"] | None = None
+    # list of fine-tune job objects
+    data: List[ModelResponse] | None = None

seekrai/utils/_log.py

@@ -11,14 +11,14 @@ import seekrai
 
 logger = logging.getLogger("seekrai")
 
-SEEKRFLOW_LOG = os.environ.get("SEEKRFLOW_LOG")
+SEEKR_LOG = os.environ.get("SEEKR_LOG")
 
 
 def _console_log_level() -> str | None:
     if seekrai.log in ["debug", "info"]:
         return seekrai.log
-    elif SEEKRFLOW_LOG in ["debug", "info"]:
-        return SEEKRFLOW_LOG
+    elif SEEKR_LOG in ["debug", "info"]:
+        return SEEKR_LOG
     else:
         return None
 

seekrai/utils/api_helpers.py

@@ -78,7 +78,7 @@ def default_api_key(api_key: str | None = None) -> str | None:
     """
     if api_key:
         return api_key
-    if os.environ.get("SEEKRFLOW_API_KEY"):
-        return os.environ.get("SEEKRFLOW_API_KEY")
+    if os.environ.get("SEEKR_API_KEY"):
+        return os.environ.get("SEEKR_API_KEY")
 
     raise error.AuthenticationError(seekrai.constants.MISSING_API_KEY_MESSAGE)

seekrai/utils/tools.py

@@ -7,7 +7,7 @@ from datetime import datetime
 
 logger = logging.getLogger("seekrai")
 
-SEEKRFLOW_LOG = os.environ.get("SEEKRFLOW_LOG")
+SEEKR_LOG = os.environ.get("SEEKR_LOG")
 
 NANODOLLAR = 1_000_000_000
 

seekrai-0.1.1.dist-info/METADATA

@@ -0,0 +1,165 @@
+Metadata-Version: 2.1
+Name: seekrai
+Version: 0.1.1
+Summary: Python client for SeekrAI
+Home-page: https://gitlab.cb.ntent.com/ml/seekr-py
+License: Apache-2.0
+Author: SeekrFlow
+Author-email: support@seekr.com
+Requires-Python: >=3.9,<4.0
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: click (>=8.1.7,<9.0.0)
+Requires-Dist: eval-type-backport (>=0.1.3,<0.3.0)
+Requires-Dist: filelock (>=3.13.1,<4.0.0)
+Requires-Dist: httpx (>=0.27.0,<0.28.0)
+Requires-Dist: numpy (>=1.23.5) ; python_version < "3.12"
+Requires-Dist: numpy (>=1.26.0) ; python_version >= "3.12"
+Requires-Dist: pillow (>=10.3.0,<11.0.0)
+Requires-Dist: pyarrow (>=10.0.1)
+Requires-Dist: pydantic (>=2.7,<3.0)
+Requires-Dist: requests (>=2.31.0,<3.0.0)
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: tqdm (>=4.66.2,<5.0.0)
+Requires-Dist: typer (>=0.9,<0.13)
+Project-URL: Homepage, https://www.seekr.com/
+Project-URL: Repository, https://gitlab.cb.ntent.com/ml/seekr-py
+Description-Content-Type: text/markdown
+
+The Seekr Python Library is the official Python client for SeekrFlow's API platform, providing a convenient way for interacting with the REST APIs and enables easy integrations with Python 3.8+ applications with easy to use synchronous and asynchronous clients.
+
+# Installation
+
+To install Seekr Python Library from PyPi, simply run:
+
+```shell Shell
+pip install --upgrade seekrai
+```
+
+## Setting up API Key
+
+> 🚧 You will need to create an account with [Seekr.com](https://seekr.com/) to obtain a SeekrFlow API Key.
+
+### Setting environment variable
+
+```shell
+export SEEKR_API_KEY=xxxxx
+```
+
+### Using the client
+
+```python
+from seekrai import SeekrFlow
+
+client = SeekrFlow(api_key="xxxxx")
+```
+
+# Usage – Python Client
+
+## Chat Completions
+
+```python
+import os
+from seekrai import SeekrFlow
+
+client = SeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+
+response = client.chat.completions.create(
+    model="meta-llama-3-8b-instruct",
+    messages=[{"role": "user", "content": "tell me about new york"}],
+)
+print(response.choices[0].message.content)
+```
+
+### Streaming
+
+```python
+import os
+from seekrai import SeekrFlow
+
+client = SeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+stream = client.chat.completions.create(
+    model="meta-llama-3-8b-instruct",
+    messages=[{"role": "user", "content": "tell me about new york"}],
+    stream=True,
+)
+
+for chunk in stream:
+    print(chunk.choices[0].delta.content or "", end="", flush=True)
+```
+
+### Async usage
+
+```python
+import os, asyncio
+from seekrai import AsyncSeekrFlow
+
+async_client = AsyncSeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+messages = [
+    "What are the top things to do in San Francisco?",
+    "What country is Paris in?",
+]
+
+
+async def async_chat_completion(messages):
+    async_client = AsyncSeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+    tasks = [
+        async_client.chat.completions.create(
+            model="meta-llama-3-8b-instruct",
+            messages=[{"role": "user", "content": message}],
+        )
+        for message in messages
+    ]
+    responses = await asyncio.gather(*tasks)
+
+    for response in responses:
+        print(response.choices[0].message.content)
+
+
+asyncio.run(async_chat_completion(messages))
+```
+
+## Files
+
+The files API is used for fine-tuning and allows developers to upload data to fine-tune on. It also has several methods to list all files, retrieve files, and delete files
+
+```python
+import os
+from seekrai import SeekrFlow
+
+client = SeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+
+client.files.upload(file="somedata.parquet")  # uploads a file
+client.files.list()  # lists all uploaded files
+client.files.retrieve(id="file-d0d318cb-b7d9-493a-bd70-1cfe089d3815")  # retrieves a specific file
+client.files.delete(id="file-d0d318cb-b7d9-493a-bd70-1cfe089d3815")  # deletes a file
+```
+
+## Fine-tunes
+
+The finetune API is used for fine-tuning and allows developers to create finetuning jobs. It also has several methods to list all jobs, retrieve statuses and get checkpoints.
+
+```python
+import os
+from seekrai import SeekrFlow
+
+client = SeekrFlow(api_key=os.environ.get("SEEKR_API_KEY"))
+
+client.fine_tuning.create(
+    training_file='file-d0d318cb-b7d9-493a-bd70-1cfe089d3815',
+    model='meta-llama-3-8b-instruct',
+    n_epochs=3,
+    n_checkpoints=1,
+    batch_size=4,
+    learning_rate=1e-5,
+    suffix='my-demo-finetune',
+)
+client.fine_tuning.list()  # lists all fine-tuned jobs
+client.fine_tuning.retrieve(id="ft-c66a5c18-1d6d-43c9-94bd-32d756425b4b")  # retrieves information on finetune event
+```
+

seekrai-0.1.1.dist-info/RECORD

@@ -0,0 +1,39 @@
+seekrai/__init__.py,sha256=HC6iy-IdwqecabH-6a80Lsy9qO2PBToAI0WqEErV41c,935
+seekrai/abstract/__init__.py,sha256=wNiOTW9TJpUgfCJCG-wAbhhWWH2PtoVpAuL3nxvQGps,56
+seekrai/abstract/api_requestor.py,sha256=-HExlMVUD52pXWhnJTrlVbqWj3Cpi5ut-lz-YrzkUV8,18027
+seekrai/client.py,sha256=PpI8-lRePkzhHLuiPD7ikuxImw0DAFljlmU6osL_Asg,4780
+seekrai/constants.py,sha256=Z5VWSveTfNV3igjjhxZ1S6KOB8gwWA5rKbdfyW8lWuM,1855
+seekrai/error.py,sha256=rAYL8qEd8INwYMMKvhS-HKeC3QkWL4Wq-zfazFU-zBg,4861
+seekrai/filemanager.py,sha256=bFmkJRtw7uavjfnoCV4Bykph-zle4AoJargsgHe-ybE,9917
+seekrai/resources/__init__.py,sha256=6m1J5kXqJFHqDzQkWy5Us-q3Ug1YZWWP1oQtJ_IGsRM,694
+seekrai/resources/chat/__init__.py,sha256=KmtPupgECtEN80NyvcnSmieTAFXhwmVxhMHP0qhspA4,618
+seekrai/resources/chat/completions.py,sha256=v0Nwr7lJk6d5fZ-s6ut2BLDr9Vay8qGL9ZQLRgyOve0,11047
+seekrai/resources/completions.py,sha256=w3La3zPMlN00y-b-tJwLgvZVH-xK_dKC6ktI5Ggn1us,8564
+seekrai/resources/embeddings.py,sha256=3lohUrkdFqzSg8FgS7p4r87jwjE0NXU1PilWv278quk,2705
+seekrai/resources/files.py,sha256=cl3qjiMLZiTQuNypydISq6JczSOiPfFRlNEAdB3CU6o,4921
+seekrai/resources/finetune.py,sha256=fXLkVCTnfoeq4TvjhEWQsdIwO247tcpfWCVTlWZczDw,11271
+seekrai/resources/images.py,sha256=E48lAe7YsZ2WXBHR_qz4SF7P4Y-U7t61m_bWNS91pM0,4802
+seekrai/resources/models.py,sha256=4swgCu95Y-v3TF0yixHGW9djLYlNsQEFO64zcor-PTs,4863
+seekrai/seekrflow_response.py,sha256=5RFEQzamDy7sTSDkxSsZQThZ3biNmeCPeHWdrFId5Go,1320
+seekrai/types/__init__.py,sha256=YFbBhp3f0HJGdKYFAy1TVMxQp8pe4ggLVXjsnMVAGVc,1555
+seekrai/types/abstract.py,sha256=TqWFQV_6bPblywfCH-r8FCkXWvPkc9KlJ4QVgyrnaMc,642
+seekrai/types/chat_completions.py,sha256=GgqEcfdjkWecPVZEHRENctQ1SQ6KB4CculxyKhkvnHo,3571
+seekrai/types/common.py,sha256=79fvG60otq-H4QL0OULgmxUAAOKKas4YSYycLDLl7To,1430
+seekrai/types/completions.py,sha256=lm9AFdZR3Xg5AHPkV-qETHikkwMJmkHrLGr5GG-YR-M,2171
+seekrai/types/embeddings.py,sha256=OANoLNOs0aceS8NppVvvcNYQbF7-pAOAmcr30pw64OU,749
+seekrai/types/error.py,sha256=uTKISs9aRC4_6zwirtNkanxepN8KY-SqCq0kNbfZylQ,370
+seekrai/types/files.py,sha256=A2B8OPasUQVSkNdxkzpv2y9I2B7vuNCq64KGqwRanKo,2025
+seekrai/types/finetune.py,sha256=mMS_3vJnJG2bBGWHCo3t98iieglwe_kR9sOrxfnO3xY,5825
+seekrai/types/images.py,sha256=Fusj8OhVYFsT8kz636lRGGivLbPXo_ZNgakKwmzJi3U,914
+seekrai/types/models.py,sha256=1ZfW9WwayApkISRizDntjkWhYNv-wkbrRVIfHn2QuC4,1242
+seekrai/utils/__init__.py,sha256=dfbiYEc47EBVRkq6C4O9y6tTGuPuV3LbV3__v01Mbds,658
+seekrai/utils/_log.py,sha256=Cayw5B394H2WGVTXPXS2AN8znQdxsgrLqADXgqmokvU,1649
+seekrai/utils/api_helpers.py,sha256=0Y8BblNIr9h_R12zdmhkxgTlxgoRkbq84QNi4nNWGu8,2385
+seekrai/utils/files.py,sha256=B61Pwra49MVVWjPtdkx4hBtAuUe9UI63hdNus87Uq0o,7164
+seekrai/utils/tools.py,sha256=jgJTL-dOIouDbEJLdQpQfpXhqaz_poQYS52adyUtBjo,1781
+seekrai/version.py,sha256=q6iGQVFor8zXiPP5F-3vy9TndOxKv5JXbaNJ2kdOQws,125
+seekrai-0.1.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+seekrai-0.1.1.dist-info/METADATA,sha256=mhkNjlZLyOPwkwd8PJQ5hCQO0jslB9sDov-UJBSfGZk,4840
+seekrai-0.1.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+seekrai-0.1.1.dist-info/entry_points.txt,sha256=N49yOEGi1sK7Xr13F_rkkcOxQ88suyiMoOmRhUHTZ_U,48
+seekrai-0.1.1.dist-info/RECORD,,

seekrai/cli/api/chat.py

@@ -1,245 +0,0 @@
-from __future__ import annotations
-
-import cmd
-import json
-from typing import List, Tuple
-
-import click
-
-from seekrai import seekrflow
-from seekrai.types.chat_completions import (
-    ChatCompletionChoicesChunk,
-    ChatCompletionChunk,
-    ChatCompletionResponse,
-)
-
-
-class ChatShell(cmd.Cmd):
-    intro = "Type /exit to exit, /help, or /? to list commands.\n"
-    prompt = ">>> "
-
-    def __init__(
-        self,
-        client: SeekrFlow,
-        model: str,
-        max_tokens: int | None = None,
-        stop: List[str] | None = None,
-        temperature: float | None = None,
-        top_p: float | None = None,
-        top_k: int | None = None,
-        repetition_penalty: float | None = None,
-        safety_model: str | None = None,
-        system_message: str | None = None,
-    ) -> None:
-        super().__init__()
-        self.client = client
-        self.model = model
-        self.max_tokens = max_tokens
-        self.stop = stop
-        self.temperature = temperature
-        self.top_p = top_p
-        self.top_k = top_k
-        self.repetition_penalty = repetition_penalty
-        self.safety_model = safety_model
-        self.system_message = system_message
-
-        self.messages = (
-            [{"role": "system", "content": self.system_message}]
-            if self.system_message
-            else []
-        )
-
-    def precmd(self, line: str) -> str:
-        if line.startswith("/"):
-            return line[1:]
-        else:
-            return "say " + line
-
-    def do_say(self, arg: str) -> None:
-        self.messages.append({"role": "user", "content": arg})
-
-        output = ""
-
-        for chunk in self.client.chat.completions.create(
-            messages=self.messages,
-            model=self.model,
-            max_tokens=self.max_tokens,
-            stop=self.stop,
-            temperature=self.temperature,
-            top_p=self.top_p,
-            top_k=self.top_k,
-            repetition_penalty=self.repetition_penalty,
-            safety_model=self.safety_model,
-            stream=True,
-        ):
-            # assertions for type checking
-            assert isinstance(chunk, ChatCompletionChunk)
-            assert chunk.choices
-            assert chunk.choices[0].delta
-            assert chunk.choices[0].delta.content
-
-            token = chunk.choices[0].delta.content
-
-            click.echo(token, nl=False)
-
-            output += token
-
-        click.echo("\n")
-
-        self.messages.append({"role": "assistant", "content": output})
-
-    def do_reset(self, arg: str) -> None:
-        self.messages = (
-            [{"role": "system", "content": self.system_message}]
-            if self.system_message
-            else []
-        )
-
-    def do_exit(self, arg: str) -> bool:
-        return True
-
-
-@click.command(name="chat.interactive")
-@click.pass_context
-@click.option("--model", type=str, required=True, help="Model name")
-@click.option("--max-tokens", type=int, help="Max tokens to generate")
-@click.option(
-    "--stop", type=str, multiple=True, help="List of strings to stop generation"
-)
-@click.option("--temperature", type=float, help="Sampling temperature")
-@click.option("--top-p", type=int, help="Top p sampling")
-@click.option("--top-k", type=float, help="Top k sampling")
-@click.option("--safety-model", type=str, help="Moderation model")
-@click.option("--system-message", type=str, help="System message to use for the chat")
-def interactive(
-    ctx: click.Context,
-    model: str,
-    max_tokens: int | None = None,
-    stop: List[str] | None = None,
-    temperature: float | None = None,
-    top_p: float | None = None,
-    top_k: int | None = None,
-    repetition_penalty: float | None = None,
-    safety_model: str | None = None,
-    system_message: str | None = None,
-) -> None:
-    """Interactive chat shell"""
-    client: SeekrFlow = ctx.obj
-
-    ChatShell(
-        client=client,
-        model=model,
-        max_tokens=max_tokens,
-        stop=stop,
-        temperature=temperature,
-        top_p=top_p,
-        top_k=top_k,
-        repetition_penalty=repetition_penalty,
-        safety_model=safety_model,
-        system_message=system_message,
-    ).cmdloop()
-
-
-@click.command(name="chat.completions")
-@click.pass_context
-@click.option(
-    "--message",
-    type=(str, str),
-    multiple=True,
-    required=True,
-    help="Message to generate chat completions from",
-)
-@click.option("--model", type=str, required=True, help="Model name")
-@click.option("--max-tokens", type=int, help="Max tokens to generate")
-@click.option(
-    "--stop", type=str, multiple=True, help="List of strings to stop generation"
-)
-@click.option("--temperature", type=float, help="Sampling temperature")
-@click.option("--top-p", type=int, help="Top p sampling")
-@click.option("--top-k", type=float, help="Top k sampling")
-@click.option("--repetition-penalty", type=float, help="Repetition penalty")
-@click.option("--no-stream", is_flag=True, help="Disable streaming")
-@click.option("--logprobs", type=int, help="Return logprobs. Only works with --raw.")
-@click.option("--echo", is_flag=True, help="Echo prompt. Only works with --raw.")
-@click.option("--n", type=int, help="Number of output generations")
-@click.option("--safety-model", type=str, help="Moderation model")
-@click.option("--raw", is_flag=True, help="Output raw JSON")
-def chat(
-    ctx: click.Context,
-    message: List[Tuple[str, str]],
-    model: str,
-    max_tokens: int | None = None,
-    stop: List[str] | None = None,
-    temperature: float | None = None,
-    top_p: float | None = None,
-    top_k: int | None = None,
-    repetition_penalty: float | None = None,
-    no_stream: bool = False,
-    logprobs: int | None = None,
-    echo: bool | None = None,
-    n: int | None = None,
-    safety_model: str | None = None,
-    raw: bool = False,
-) -> None:
-    """Generate chat completions from messages"""
-    client: SeekrFlow = ctx.obj
-
-    messages = [{"role": msg[0], "content": msg[1]} for msg in message]
-
-    response = client.chat.completions.create(
-        model=model,
-        messages=messages,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        max_tokens=max_tokens,
-        stop=stop,
-        repetition_penalty=repetition_penalty,
-        stream=not no_stream,
-        logprobs=logprobs,
-        echo=echo,
-        n=n,
-        safety_model=safety_model,
-    )
-
-    if not no_stream:
-        for chunk in response:
-            # assertions for type checking
-            assert isinstance(chunk, ChatCompletionChunk)
-            assert chunk.choices
-
-            if raw:
-                click.echo(f"{json.dumps(chunk.model_dump())}")
-                continue
-
-            should_print_header = len(chunk.choices) > 1
-            for stream_choice in sorted(chunk.choices, key=lambda c: c.index):  # type: ignore
-                assert isinstance(stream_choice, ChatCompletionChoicesChunk)
-                assert stream_choice.delta
-
-                if should_print_header:
-                    click.echo(f"\n===== Completion {stream_choice.index} =====\n")
-                click.echo(f"{stream_choice.delta.content}", nl=False)
-
-                if should_print_header:
-                    click.echo("\n")
-
-        # new line after stream ends
-        click.echo("\n")
-    else:
-        # assertions for type checking
-        assert isinstance(response, ChatCompletionResponse)
-        assert isinstance(response.choices, list)
-
-        if raw:
-            click.echo(f"{json.dumps(response.model_dump(), indent=4)}")
-            return
-
-        should_print_header = len(response.choices) > 1
-        for i, choice in enumerate(response.choices):
-            if should_print_header:
-                click.echo(f"===== Completion {i} =====")
-            click.echo(choice.message.content)  # type: ignore
-
-            if should_print_header:
-                click.echo("\n")

seekrai/cli/api/completions.py

@@ -1,107 +0,0 @@
-from __future__ import annotations
-
-import json
-from typing import List
-
-import click
-
-from seekrai import seekrflow
-from seekrai.types import CompletionChunk
-from seekrai.types.completions import CompletionChoicesChunk, CompletionResponse
-
-
-@click.command()
-@click.pass_context
-@click.argument("prompt", type=str, required=True)
-@click.option("--model", type=str, required=True, help="Model name")
-@click.option("--no-stream", is_flag=True, help="Disable streaming")
-@click.option("--max-tokens", type=int, help="Max tokens to generate")
-@click.option(
-    "--stop", type=str, multiple=True, help="List of strings to stop generation"
-)
-@click.option("--temperature", type=float, help="Sampling temperature")
-@click.option("--top-p", type=int, help="Top p sampling")
-@click.option("--top-k", type=float, help="Top k sampling")
-@click.option("--logprobs", type=int, help="Return logprobs. Only works with --raw.")
-@click.option("--echo", is_flag=True, help="Echo prompt. Only works with --raw.")
-@click.option("--n", type=int, help="Number of output generations")
-@click.option("--safety-model", type=str, help="Moderation model")
-@click.option("--raw", is_flag=True, help="Return raw JSON response")
-def completions(
-    ctx: click.Context,
-    prompt: str,
-    model: str,
-    max_tokens: int | None = 512,
-    stop: List[str] | None = None,
-    temperature: float | None = None,
-    top_p: float | None = None,
-    top_k: int | None = None,
-    repetition_penalty: float | None = None,
-    no_stream: bool = False,
-    logprobs: int | None = None,
-    echo: bool | None = None,
-    n: int | None = None,
-    safety_model: str | None = None,
-    raw: bool = False,
-) -> None:
-    """Generate text completions"""
-    client: SeekrFlow = ctx.obj
-
-    response = client.completions.create(
-        model=model,
-        prompt=prompt,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        max_tokens=max_tokens,
-        stop=stop,
-        repetition_penalty=repetition_penalty,
-        stream=not no_stream,
-        logprobs=logprobs,
-        echo=echo,
-        n=n,
-        safety_model=safety_model,
-    )
-
-    if not no_stream:
-        for chunk in response:
-            # assertions for type checking
-            assert isinstance(chunk, CompletionChunk)
-            assert chunk.choices
-
-            if raw:
-                click.echo(f"{json.dumps(chunk.model_dump())}")
-                continue
-
-            should_print_header = len(chunk.choices) > 1
-            for stream_choice in sorted(chunk.choices, key=lambda c: c.index):  # type: ignore
-                # assertions for type checking
-                assert isinstance(stream_choice, CompletionChoicesChunk)
-                assert stream_choice.delta
-
-                if should_print_header:
-                    click.echo(f"\n===== Completion {stream_choice.index} =====\n")
-                click.echo(f"{stream_choice.delta.content}", nl=False)
-
-                if should_print_header:
-                    click.echo("\n")
-
-        # new line after stream ends
-        click.echo("\n")
-    else:
-        # assertions for type checking
-        assert isinstance(response, CompletionResponse)
-        assert isinstance(response.choices, list)
-
-        if raw:
-            click.echo(f"{json.dumps(response.model_dump(), indent=4)}")
-            return
-
-        should_print_header = len(response.choices) > 1
-        for i, choice in enumerate(response.choices):
-            if should_print_header:
-                click.echo(f"===== Completion {i} =====")
-            click.echo(choice.text)
-
-            if should_print_header or not choice.text.endswith("\n"):
-                click.echo("\n")