{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# OpenAI Compatible API\n", "\n", "SGLang provides an OpenAI compatible API for smooth transition from OpenAI services. Full reference of the API is available at [OpenAI API Reference](https://platform.openai.com/docs/api-reference).\n", "\n", "This tutorial covers these popular APIs:\n", "\n", "- `chat/completions`\n", "- `completions`\n", "- `batches`\n", "- `embeddings`(refer to [embedding_model.ipynb](embedding_model.ipynb))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Chat Completions\n", "\n", "### Usage\n", "\n", "Similar to [send_request.ipynb](send_request.ipynb), we can send a chat completion request to SGLang server with OpenAI API format." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:44:46.419815Z", "iopub.status.busy": "2024-11-01T02:44:46.419509Z", "iopub.status.idle": "2024-11-01T02:45:16.621648Z", "shell.execute_reply": "2024-11-01T02:45:16.620659Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:44:51] server_args=ServerArgs(model_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='meta-llama/Meta-Llama-3.1-8B-Instruct', chat_template=None, is_embedding=False, host='0.0.0.0', port=30000, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=357249111, constrained_json_whitespace_pattern=None, decode_log_interval=40, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n", " warnings.warn(\n", "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:44:57 TP0] Init torch distributed begin.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:44:58 TP0] Load weight begin. avail mem=47.27 GB\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:44:59 TP0] lm_eval is not installed, GPTQ may not be usable\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO 10-31 19:44:59 weight_utils.py:243] Using model weights format ['*.safetensors']\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00

NOTE: Typically, the server runs in a separate terminal.
In this notebook, we run the server and notebook code together, so their outputs are combined.
To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from sglang.utils import (\n", " execute_shell_command,\n", " wait_for_server,\n", " terminate_process,\n", " print_highlight,\n", ")\n", "\n", "server_process = execute_shell_command(\n", " command=\"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0\"\n", ")\n", "\n", "wait_for_server(\"http://localhost:30000\")" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:16.624550Z", "iopub.status.busy": "2024-11-01T02:45:16.624258Z", "iopub.status.idle": "2024-11-01T02:45:18.087455Z", "shell.execute_reply": "2024-11-01T02:45:18.086450Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:16 TP0] Prefill batch. #new-seq: 1, #new-token: 48, #cached-token: 1, cache hit rate: 1.79%, token usage: 0.00, #running-req: 0, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:17 TP0] Decode batch. #running-req: 1, #token: 82, token usage: 0.00, gen throughput (token/s): 5.21, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:18] INFO: 127.0.0.1:37738 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Response: ChatCompletion(id='e04fce6c460d4764af68007fc82763e1', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='Here are 3 countries and their capitals:\\n\\n1. **Country:** Japan\\n**Capital:** Tokyo\\n\\n2. **Country:** Australia\\n**Capital:** Canberra\\n\\n3. **Country:** Brazil\\n**Capital:** Brasília', refusal=None, role='assistant', function_call=None, tool_calls=None), matched_stop=128009)], created=1730429118, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=46, prompt_tokens=49, total_tokens=95, prompt_tokens_details=None))" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import openai\n", "\n", "client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n", "\n", "response = client.chat.completions.create(\n", " model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " messages=[\n", " {\"role\": \"system\", \"content\": \"You are a helpful AI assistant\"},\n", " {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n", " ],\n", " temperature=0,\n", " max_tokens=64,\n", ")\n", "\n", "print_highlight(f\"Response: {response}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Parameters\n", "\n", "The chat completions API accepts OpenAI Chat Completions API's parameters. Refer to [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat/create) for more details.\n", "\n", "Here is an example of a detailed chat completion request:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:18.090228Z", "iopub.status.busy": "2024-11-01T02:45:18.090071Z", "iopub.status.idle": "2024-11-01T02:45:21.193221Z", "shell.execute_reply": "2024-11-01T02:45:21.192539Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:18 TP0] Prefill batch. #new-seq: 1, #new-token: 48, #cached-token: 28, cache hit rate: 21.97%, token usage: 0.00, #running-req: 0, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:18 TP0] Decode batch. #running-req: 1, #token: 104, token usage: 0.00, gen throughput (token/s): 39.15, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:19 TP0] Decode batch. #running-req: 1, #token: 144, token usage: 0.00, gen throughput (token/s): 41.80, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:20 TP0] Decode batch. #running-req: 1, #token: 184, token usage: 0.00, gen throughput (token/s): 41.81, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:21] INFO: 127.0.0.1:37738 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Ancient Rome's major achievements include:

1. **Engineering and Architecture**: They built iconic structures like the Colosseum, Pantheon, and Roman Forum, showcasing their mastery of concrete, arches, and aqueducts.
2. **Law and Governance**: The Romans developed the 12 Tables (450 BCE), which formed the basis of their laws, and established the concept of citizenship, paving the way for modern democracy.
3. **Military Conquests**: Rome expanded its territories through a series of wars, creating a vast empire that lasted for centuries, stretching from Britain to Egypt.
4. **Language and Literature**: Latin became" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "response = client.chat.completions.create(\n", " model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " messages=[\n", " {\n", " \"role\": \"system\",\n", " \"content\": \"You are a knowledgeable historian who provides concise responses.\",\n", " },\n", " {\"role\": \"user\", \"content\": \"Tell me about ancient Rome\"},\n", " {\n", " \"role\": \"assistant\",\n", " \"content\": \"Ancient Rome was a civilization centered in Italy.\",\n", " },\n", " {\"role\": \"user\", \"content\": \"What were their major achievements?\"},\n", " ],\n", " temperature=0.3, # Lower temperature for more focused responses\n", " max_tokens=128, # Reasonable length for a concise response\n", " top_p=0.95, # Slightly higher for better fluency\n", " presence_penalty=0.2, # Mild penalty to avoid repetition\n", " frequency_penalty=0.2, # Mild penalty for more natural language\n", " n=1, # Single response is usually more stable\n", " seed=42, # Keep for reproducibility\n", ")\n", "\n", "print_highlight(response.choices[0].message.content)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Streaming mode is also supported" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:21.195226Z", "iopub.status.busy": "2024-11-01T02:45:21.194680Z", "iopub.status.idle": "2024-11-01T02:45:21.675473Z", "shell.execute_reply": "2024-11-01T02:45:21.675050Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:21] INFO: 127.0.0.1:37738 - \"POST /v1/chat/completions HTTP/1.1\" 200 OK\n", "[2024-10-31 19:45:21 TP0] Prefill batch. #new-seq: 1, #new-token: 15, #cached-token: 25, cache hit rate: 31.40%, token usage: 0.00, #running-req: 0, #queue-req: 0\n", "It looks like you're ready to" ] }, { "name": "stdout", "output_type": "stream", "text": [ " begin" ] }, { "name": "stdout", "output_type": "stream", "text": [ ". What kind of test would you like" ] }, { "name": "stdout", "output_type": "stream", "text": [ " to" ] }, { "name": "stdout", "output_type": "stream", "text": [ " conduct?" ] } ], "source": [ "stream = client.chat.completions.create(\n", " model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " messages=[{\"role\": \"user\", \"content\": \"Say this is a test\"}],\n", " stream=True,\n", ")\n", "for chunk in stream:\n", " if chunk.choices[0].delta.content is not None:\n", " print(chunk.choices[0].delta.content, end=\"\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Completions\n", "\n", "### Usage\n", "\n", "Completions API is similar to Chat Completions API, but without the `messages` parameter." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:21.676813Z", "iopub.status.busy": "2024-11-01T02:45:21.676665Z", "iopub.status.idle": "2024-11-01T02:45:23.182104Z", "shell.execute_reply": "2024-11-01T02:45:23.181695Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:21 TP0] Prefill batch. #new-seq: 1, #new-token: 8, #cached-token: 1, cache hit rate: 30.39%, token usage: 0.00, #running-req: 0, #queue-req: 0\n", "[2024-10-31 19:45:21 TP0] Decode batch. #running-req: 1, #token: 11, token usage: 0.00, gen throughput (token/s): 39.18, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:22 TP0] Decode batch. #running-req: 1, #token: 51, token usage: 0.00, gen throughput (token/s): 42.85, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:23] INFO: 127.0.0.1:37738 - \"POST /v1/completions HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Response: Completion(id='84ca7b4df182449697c4b38a454b8834', choices=[CompletionChoice(finish_reason='length', index=0, logprobs=None, text=' 1. 2. 3.\\n1. United States Washington D.C. 2. Japan Tokyo 3. Australia Canberra\\nList 3 countries and their capitals. 1. 2. 3.\\n1. China Beijing 2. Brazil Bras', matched_stop=None)], created=1730429123, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='text_completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=64, prompt_tokens=9, total_tokens=73, prompt_tokens_details=None))" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "response = client.completions.create(\n", " model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " prompt=\"List 3 countries and their capitals.\",\n", " temperature=0,\n", " max_tokens=64,\n", " n=1,\n", " stop=None,\n", ")\n", "\n", "print_highlight(f\"Response: {response}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Parameters\n", "\n", "The completions API accepts OpenAI Completions API's parameters. Refer to [OpenAI Completions API](https://platform.openai.com/docs/api-reference/completions/create) for more details.\n", "\n", "Here is an example of a detailed completions request:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:23.186337Z", "iopub.status.busy": "2024-11-01T02:45:23.186189Z", "iopub.status.idle": "2024-11-01T02:45:26.769744Z", "shell.execute_reply": "2024-11-01T02:45:26.769299Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:23 TP0] Prefill batch. #new-seq: 1, #new-token: 9, #cached-token: 1, cache hit rate: 29.32%, token usage: 0.00, #running-req: 0, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:23 TP0] Decode batch. #running-req: 1, #token: 29, token usage: 0.00, gen throughput (token/s): 40.76, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:24 TP0] Decode batch. #running-req: 1, #token: 69, token usage: 0.00, gen throughput (token/s): 42.13, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:25 TP0] Decode batch. #running-req: 1, #token: 109, token usage: 0.00, gen throughput (token/s): 42.01, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:26 TP0] Decode batch. #running-req: 1, #token: 149, token usage: 0.00, gen throughput (token/s): 41.87, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:26] INFO: 127.0.0.1:37738 - \"POST /v1/completions HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Response: Completion(id='fe384c17aece4a5ca5fb5238dcd1adec', choices=[CompletionChoice(finish_reason='length', index=0, logprobs=None, text=\" This can be a sci-fi story, and you have the ability to create a unique and imaginative universe.\\nIn the depths of space, a lone space explorer named Kaelin Vex navigated through the swirling vortex of the Aurora Nebula. Her ship, the Starweaver, was an extension of herself, its advanced AI system linked directly to her mind. Together, they danced through the cosmos, searching for answers to the mysteries of the universe.\\nKaelin's mission was to uncover the secrets of the ancient alien civilization known as the Architects. Legends spoke of their unparalleled technological prowess and their ability to manipulate reality itself. Many believed they had transcended their physical forms, becoming one with the cosmos.\\nAs Kaelin delved deeper into\", matched_stop=None)], created=1730429126, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='text_completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=150, prompt_tokens=10, total_tokens=160, prompt_tokens_details=None))" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "response = client.completions.create(\n", " model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " prompt=\"Write a short story about a space explorer.\",\n", " temperature=0.7, # Moderate temperature for creative writing\n", " max_tokens=150, # Longer response for a story\n", " top_p=0.9, # Balanced diversity in word choice\n", " stop=[\"\\n\\n\", \"THE END\"], # Multiple stop sequences\n", " presence_penalty=0.3, # Encourage novel elements\n", " frequency_penalty=0.3, # Reduce repetitive phrases\n", " n=1, # Generate one completion\n", " seed=123, # For reproducible results\n", ")\n", "\n", "print_highlight(f\"Response: {response}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Batches\n", "\n", "We have implemented the batches API for chat completions and completions. You can upload your requests in `jsonl` files, create a batch job, and retrieve the results when the batch job is completed (which takes longer but costs less).\n", "\n", "The batches APIs are:\n", "\n", "- `batches`\n", "- `batches/{batch_id}/cancel`\n", "- `batches/{batch_id}`\n", "\n", "Here is an example of a batch job for chat completions, completions are similar.\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:26.772016Z", "iopub.status.busy": "2024-11-01T02:45:26.771868Z", "iopub.status.idle": "2024-11-01T02:45:26.794225Z", "shell.execute_reply": "2024-11-01T02:45:26.793811Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:26] INFO: 127.0.0.1:57182 - \"POST /v1/files HTTP/1.1\" 200 OK\n", "[2024-10-31 19:45:26] INFO: 127.0.0.1:57182 - \"POST /v1/batches HTTP/1.1\" 200 OK\n", "[2024-10-31 19:45:26 TP0] Prefill batch. #new-seq: 2, #new-token: 20, #cached-token: 60, cache hit rate: 42.80%, token usage: 0.00, #running-req: 0, #queue-req: 0\n" ] }, { "data": { "text/html": [ "Batch job created with ID: batch_d9af5b49-ad3d-423e-8c30-4aaafa5c18c4" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import json\n", "import time\n", "from openai import OpenAI\n", "\n", "client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n", "\n", "requests = [\n", " {\n", " \"custom_id\": \"request-1\",\n", " \"method\": \"POST\",\n", " \"url\": \"/chat/completions\",\n", " \"body\": {\n", " \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " \"messages\": [\n", " {\"role\": \"user\", \"content\": \"Tell me a joke about programming\"}\n", " ],\n", " \"max_tokens\": 50,\n", " },\n", " },\n", " {\n", " \"custom_id\": \"request-2\",\n", " \"method\": \"POST\",\n", " \"url\": \"/chat/completions\",\n", " \"body\": {\n", " \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " \"messages\": [{\"role\": \"user\", \"content\": \"What is Python?\"}],\n", " \"max_tokens\": 50,\n", " },\n", " },\n", "]\n", "\n", "input_file_path = \"batch_requests.jsonl\"\n", "\n", "with open(input_file_path, \"w\") as f:\n", " for req in requests:\n", " f.write(json.dumps(req) + \"\\n\")\n", "\n", "with open(input_file_path, \"rb\") as f:\n", " file_response = client.files.create(file=f, purpose=\"batch\")\n", "\n", "batch_response = client.batches.create(\n", " input_file_id=file_response.id,\n", " endpoint=\"/v1/chat/completions\",\n", " completion_window=\"24h\",\n", ")\n", "\n", "print_highlight(f\"Batch job created with ID: {batch_response.id}\")" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:26.796422Z", "iopub.status.busy": "2024-11-01T02:45:26.796273Z", "iopub.status.idle": "2024-11-01T02:45:29.810471Z", "shell.execute_reply": "2024-11-01T02:45:29.810041Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:27 TP0] Decode batch. #running-req: 1, #token: 69, token usage: 0.00, gen throughput (token/s): 51.72, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Batch job status: validating...trying again in 3 seconds...\n", "[2024-10-31 19:45:29] INFO: 127.0.0.1:57182 - \"GET /v1/batches/batch_d9af5b49-ad3d-423e-8c30-4aaafa5c18c4 HTTP/1.1\" 200 OK\n", "Batch job completed successfully!\n", "Request counts: BatchRequestCounts(completed=2, failed=0, total=2)\n", "[2024-10-31 19:45:29] INFO: 127.0.0.1:57182 - \"GET /v1/files/backend_result_file-4ed79bf4-1e07-4fa9-9638-7448aa4e074b/content HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Request request-1:" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Response: {'status_code': 200, 'request_id': 'request-1', 'body': {'id': 'request-1', 'object': 'chat.completion', 'created': 1730429127, 'model': 'meta-llama/Meta-Llama-3.1-8B-Instruct', 'choices': {'index': 0, 'message': {'role': 'assistant', 'content': 'Why do programmers prefer dark mode?\\n\\nBecause light attracts bugs.'}, 'logprobs': None, 'finish_reason': 'stop', 'matched_stop': 128009}, 'usage': {'prompt_tokens': 41, 'completion_tokens': 13, 'total_tokens': 54}, 'system_fingerprint': None}}" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request request-2:" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Response: {'status_code': 200, 'request_id': 'request-2', 'body': {'id': 'request-2', 'object': 'chat.completion', 'created': 1730429127, 'model': 'meta-llama/Meta-Llama-3.1-8B-Instruct', 'choices': {'index': 0, 'message': {'role': 'assistant', 'content': '**What is Python?**\\n\\nPython is a high-level, interpreted programming language that is widely used for various purposes such as web development, scientific computing, data analysis, artificial intelligence, and more. It was created in the late 1980s by'}, 'logprobs': None, 'finish_reason': 'length', 'matched_stop': None}, 'usage': {'prompt_tokens': 39, 'completion_tokens': 50, 'total_tokens': 89}, 'system_fingerprint': None}}" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Cleaning up files..." ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:29] INFO: 127.0.0.1:57182 - \"DELETE /v1/files/backend_result_file-4ed79bf4-1e07-4fa9-9638-7448aa4e074b HTTP/1.1\" 200 OK\n" ] } ], "source": [ "while batch_response.status not in [\"completed\", \"failed\", \"cancelled\"]:\n", " time.sleep(3)\n", " print(f\"Batch job status: {batch_response.status}...trying again in 3 seconds...\")\n", " batch_response = client.batches.retrieve(batch_response.id)\n", "\n", "if batch_response.status == \"completed\":\n", " print(\"Batch job completed successfully!\")\n", " print(f\"Request counts: {batch_response.request_counts}\")\n", "\n", " result_file_id = batch_response.output_file_id\n", " file_response = client.files.content(result_file_id)\n", " result_content = file_response.read().decode(\"utf-8\")\n", "\n", " results = [\n", " json.loads(line) for line in result_content.split(\"\\n\") if line.strip() != \"\"\n", " ]\n", "\n", " for result in results:\n", " print_highlight(f\"Request {result['custom_id']}:\")\n", " print_highlight(f\"Response: {result['response']}\")\n", "\n", " print_highlight(\"Cleaning up files...\")\n", " # Only delete the result file ID since file_response is just content\n", " client.files.delete(result_file_id)\n", "else:\n", " print_highlight(f\"Batch job failed with status: {batch_response.status}\")\n", " if hasattr(batch_response, \"errors\"):\n", " print_highlight(f\"Errors: {batch_response.errors}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It takes a while to complete the batch job. You can use these two APIs to retrieve the batch job status or cancel the batch job.\n", "\n", "1. `batches/{batch_id}`: Retrieve the batch job status.\n", "2. `batches/{batch_id}/cancel`: Cancel the batch job.\n", "\n", "Here is an example to check the batch job status." ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:29.812339Z", "iopub.status.busy": "2024-11-01T02:45:29.812198Z", "iopub.status.idle": "2024-11-01T02:45:54.851243Z", "shell.execute_reply": "2024-11-01T02:45:54.850668Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:29] INFO: 127.0.0.1:57186 - \"POST /v1/files HTTP/1.1\" 200 OK\n", "[2024-10-31 19:45:29] INFO: 127.0.0.1:57186 - \"POST /v1/batches HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Created batch job with ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Initial status: validating" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:29 TP0] Prefill batch. #new-seq: 27, #new-token: 810, #cached-token: 675, cache hit rate: 45.05%, token usage: 0.00, #running-req: 0, #queue-req: 0\n", "[2024-10-31 19:45:29 TP0] Prefill batch. #new-seq: 73, #new-token: 2190, #cached-token: 1825, cache hit rate: 45.33%, token usage: 0.00, #running-req: 27, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:30 TP0] Decode batch. #running-req: 100, #token: 5125, token usage: 0.02, gen throughput (token/s): 636.38, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:31 TP0] Decode batch. #running-req: 100, #token: 9125, token usage: 0.04, gen throughput (token/s): 3507.97, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:33 TP0] Decode batch. #running-req: 100, #token: 13125, token usage: 0.06, gen throughput (token/s): 3417.06, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:34 TP0] Decode batch. #running-req: 100, #token: 17125, token usage: 0.08, gen throughput (token/s): 3332.03, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:35 TP0] Decode batch. #running-req: 100, #token: 21125, token usage: 0.10, gen throughput (token/s): 3252.29, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:36 TP0] Decode batch. #running-req: 100, #token: 25125, token usage: 0.12, gen throughput (token/s): 3173.87, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:38 TP0] Decode batch. #running-req: 100, #token: 29125, token usage: 0.13, gen throughput (token/s): 3101.31, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:39 TP0] Decode batch. #running-req: 100, #token: 33125, token usage: 0.15, gen throughput (token/s): 3030.90, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:39] INFO: 127.0.0.1:37782 - \"GET /v1/batches/batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Batch job details (check 1 / 5) // ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 // Status: in_progress // Created at: 1730429129 // Input file ID: backend_input_file-f42b27b5-05ee-4d27-9a37-ff04c3b4a427 // Output file ID: None" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request counts: Total: 0 // Completed: 0 // Failed: 0" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:40 TP0] Decode batch. #running-req: 100, #token: 37125, token usage: 0.17, gen throughput (token/s): 2961.37, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:42 TP0] Decode batch. #running-req: 100, #token: 41125, token usage: 0.19, gen throughput (token/s): 2899.29, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:42] INFO: 127.0.0.1:37782 - \"GET /v1/batches/batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Batch job details (check 2 / 5) // ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 // Status: in_progress // Created at: 1730429129 // Input file ID: backend_input_file-f42b27b5-05ee-4d27-9a37-ff04c3b4a427 // Output file ID: None" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request counts: Total: 0 // Completed: 0 // Failed: 0" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:43 TP0] Decode batch. #running-req: 100, #token: 45125, token usage: 0.21, gen throughput (token/s): 2836.50, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:45 TP0] Decode batch. #running-req: 100, #token: 49125, token usage: 0.23, gen throughput (token/s): 2777.80, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:45] INFO: 127.0.0.1:37782 - \"GET /v1/batches/batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Batch job details (check 3 / 5) // ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 // Status: in_progress // Created at: 1730429129 // Input file ID: backend_input_file-f42b27b5-05ee-4d27-9a37-ff04c3b4a427 // Output file ID: None" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request counts: Total: 0 // Completed: 0 // Failed: 0" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:48] INFO: 127.0.0.1:37782 - \"GET /v1/batches/batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Batch job details (check 4 / 5) // ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 // Status: completed // Created at: 1730429129 // Input file ID: backend_input_file-f42b27b5-05ee-4d27-9a37-ff04c3b4a427 // Output file ID: backend_result_file-dc391511-07f2-4f94-90cb-3ed09bc4b8a3" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request counts: Total: 100 // Completed: 100 // Failed: 0" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:51] INFO: 127.0.0.1:37782 - \"GET /v1/batches/batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Batch job details (check 5 / 5) // ID: batch_3d1a7f8e-af5a-4a14-8391-1001aadfe1b2 // Status: completed // Created at: 1730429129 // Input file ID: backend_input_file-f42b27b5-05ee-4d27-9a37-ff04c3b4a427 // Output file ID: backend_result_file-dc391511-07f2-4f94-90cb-3ed09bc4b8a3" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Request counts: Total: 100 // Completed: 100 // Failed: 0" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import json\n", "import time\n", "from openai import OpenAI\n", "\n", "client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n", "\n", "requests = []\n", "for i in range(100):\n", " requests.append(\n", " {\n", " \"custom_id\": f\"request-{i}\",\n", " \"method\": \"POST\",\n", " \"url\": \"/chat/completions\",\n", " \"body\": {\n", " \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " \"messages\": [\n", " {\n", " \"role\": \"system\",\n", " \"content\": f\"{i}: You are a helpful AI assistant\",\n", " },\n", " {\n", " \"role\": \"user\",\n", " \"content\": \"Write a detailed story about topic. Make it very long.\",\n", " },\n", " ],\n", " \"max_tokens\": 500,\n", " },\n", " }\n", " )\n", "\n", "input_file_path = \"batch_requests.jsonl\"\n", "with open(input_file_path, \"w\") as f:\n", " for req in requests:\n", " f.write(json.dumps(req) + \"\\n\")\n", "\n", "with open(input_file_path, \"rb\") as f:\n", " uploaded_file = client.files.create(file=f, purpose=\"batch\")\n", "\n", "batch_job = client.batches.create(\n", " input_file_id=uploaded_file.id,\n", " endpoint=\"/v1/chat/completions\",\n", " completion_window=\"24h\",\n", ")\n", "\n", "print_highlight(f\"Created batch job with ID: {batch_job.id}\")\n", "print_highlight(f\"Initial status: {batch_job.status}\")\n", "\n", "time.sleep(10)\n", "\n", "max_checks = 5\n", "for i in range(max_checks):\n", " batch_details = client.batches.retrieve(batch_id=batch_job.id)\n", "\n", " print_highlight(\n", " f\"Batch job details (check {i+1} / {max_checks}) // ID: {batch_details.id} // Status: {batch_details.status} // Created at: {batch_details.created_at} // Input file ID: {batch_details.input_file_id} // Output file ID: {batch_details.output_file_id}\"\n", " )\n", " print_highlight(\n", " f\"Request counts: Total: {batch_details.request_counts.total} // Completed: {batch_details.request_counts.completed} // Failed: {batch_details.request_counts.failed}\"\n", " )\n", "\n", " time.sleep(3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here is an example to cancel a batch job." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:45:54.854018Z", "iopub.status.busy": "2024-11-01T02:45:54.853851Z", "iopub.status.idle": "2024-11-01T02:46:07.893199Z", "shell.execute_reply": "2024-11-01T02:46:07.892310Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:54] INFO: 127.0.0.1:33180 - \"POST /v1/files HTTP/1.1\" 200 OK\n", "[2024-10-31 19:45:54] INFO: 127.0.0.1:33180 - \"POST /v1/batches HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Created batch job with ID: batch_c30756c3-8c09-4142-9630-9590d6124986" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Initial status: validating" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:54 TP0] Prefill batch. #new-seq: 135, #new-token: 1150, #cached-token: 6275, cache hit rate: 67.38%, token usage: 0.01, #running-req: 0, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:55 TP0] Prefill batch. #new-seq: 274, #new-token: 8192, #cached-token: 6850, cache hit rate: 55.74%, token usage: 0.02, #running-req: 135, #queue-req: 91\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:56 TP0] Prefill batch. #new-seq: 92, #new-token: 2758, #cached-token: 2302, cache hit rate: 54.19%, token usage: 0.06, #running-req: 408, #queue-req: 1\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:45:56 TP0] Decode batch. #running-req: 500, #token: 16025, token usage: 0.07, gen throughput (token/s): 409.21, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:46:00 TP0] Decode batch. #running-req: 500, #token: 36025, token usage: 0.17, gen throughput (token/s): 5777.09, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:46:03 TP0] Decode batch. #running-req: 500, #token: 56025, token usage: 0.26, gen throughput (token/s): 5530.76, #queue-req: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:46:04] INFO: 127.0.0.1:57728 - \"POST /v1/batches/batch_c30756c3-8c09-4142-9630-9590d6124986/cancel HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Cancellation initiated. Status: cancelling" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:46:07] INFO: 127.0.0.1:57728 - \"GET /v1/batches/batch_c30756c3-8c09-4142-9630-9590d6124986 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Current status: cancelled" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Batch job successfully cancelled" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[2024-10-31 19:46:07] INFO: 127.0.0.1:57728 - \"DELETE /v1/files/backend_input_file-0fbf83a7-301c-488e-a221-b702e24df6a5 HTTP/1.1\" 200 OK\n" ] }, { "data": { "text/html": [ "Successfully cleaned up input file" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Successfully deleted local batch_requests.jsonl file" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import json\n", "import time\n", "from openai import OpenAI\n", "import os\n", "\n", "client = OpenAI(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n", "\n", "requests = []\n", "for i in range(500):\n", " requests.append(\n", " {\n", " \"custom_id\": f\"request-{i}\",\n", " \"method\": \"POST\",\n", " \"url\": \"/chat/completions\",\n", " \"body\": {\n", " \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n", " \"messages\": [\n", " {\n", " \"role\": \"system\",\n", " \"content\": f\"{i}: You are a helpful AI assistant\",\n", " },\n", " {\n", " \"role\": \"user\",\n", " \"content\": \"Write a detailed story about topic. Make it very long.\",\n", " },\n", " ],\n", " \"max_tokens\": 500,\n", " },\n", " }\n", " )\n", "\n", "input_file_path = \"batch_requests.jsonl\"\n", "with open(input_file_path, \"w\") as f:\n", " for req in requests:\n", " f.write(json.dumps(req) + \"\\n\")\n", "\n", "with open(input_file_path, \"rb\") as f:\n", " uploaded_file = client.files.create(file=f, purpose=\"batch\")\n", "\n", "batch_job = client.batches.create(\n", " input_file_id=uploaded_file.id,\n", " endpoint=\"/v1/chat/completions\",\n", " completion_window=\"24h\",\n", ")\n", "\n", "print_highlight(f\"Created batch job with ID: {batch_job.id}\")\n", "print_highlight(f\"Initial status: {batch_job.status}\")\n", "\n", "time.sleep(10)\n", "\n", "try:\n", " cancelled_job = client.batches.cancel(batch_id=batch_job.id)\n", " print_highlight(f\"Cancellation initiated. Status: {cancelled_job.status}\")\n", " assert cancelled_job.status == \"cancelling\"\n", "\n", " # Monitor the cancellation process\n", " while cancelled_job.status not in [\"failed\", \"cancelled\"]:\n", " time.sleep(3)\n", " cancelled_job = client.batches.retrieve(batch_job.id)\n", " print_highlight(f\"Current status: {cancelled_job.status}\")\n", "\n", " # Verify final status\n", " assert cancelled_job.status == \"cancelled\"\n", " print_highlight(\"Batch job successfully cancelled\")\n", "\n", "except Exception as e:\n", " print_highlight(f\"Error during cancellation: {e}\")\n", " raise e\n", "\n", "finally:\n", " try:\n", " del_response = client.files.delete(uploaded_file.id)\n", " if del_response.deleted:\n", " print_highlight(\"Successfully cleaned up input file\")\n", " if os.path.exists(input_file_path):\n", " os.remove(input_file_path)\n", " print_highlight(\"Successfully deleted local batch_requests.jsonl file\")\n", " except Exception as e:\n", " print_highlight(f\"Error cleaning up: {e}\")\n", " raise e" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2024-11-01T02:46:07.896114Z", "iopub.status.busy": "2024-11-01T02:46:07.895820Z", "iopub.status.idle": "2024-11-01T02:46:09.365287Z", "shell.execute_reply": "2024-11-01T02:46:09.364705Z" } }, "outputs": [], "source": [ "terminate_process(server_process)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.7" } }, "nbformat": 4, "nbformat_minor": 2 }