Skip to main content

sageLLM protocol types and validation (Protocol v0.1)

Project description

sagellm-protocol

Protocol Compliance (Mandatory)

  • This repository defines Protocol v0.1 as the source of truth.
  • Any globally shared definitions (fields, error codes, metrics, IDs, schemas) MUST be added here before use.

CI Python Pydantic v2 Code Coverage

Type definitions and validation for sageLLM inference engine.

  • Package: isagellm-protocol
  • Import: sagellm_protocol
  • Python: 3.10+

Installation

pip install isagellm-protocol

For development:

git clone git@github.com:intellistream/sagellm-protocol.git
cd sagellm-protocol
pip install -e ".[dev]"

Features

  • Request/Response type definitions
  • Streaming event types (start/delta/end)
  • Performance metrics with validation
  • Error types and error codes
  • Timestamp tracking
  • KV cache lifecycle hooks
  • Pydantic v2 validation

Quick Start

from sagellm_protocol import Request, Response, Metrics, ErrorCode

# 创建请求
req = Request(
    request_id="req-001",
    trace_id="trace-001",
    model="llama2-7b",
    prompt="Hello, world!",
    max_tokens=128,
    stream=False,
    temperature=0.7,
)

# 创建响应
metrics = Metrics(
    ttft_ms=45.2,
    tbt_ms=12.5,
    throughput_tps=80.0,
    peak_mem_mb=24576,
    error_rate=0.0,
)

resp = Response(
    request_id="req-001",
    trace_id="trace-001",
    output_text="Hi there!",
    output_tokens=[42, 17],
    finish_reason="stop",
    metrics=metrics,
)

For more examples, see examples/basic_usage.py.

API Reference

Core Types

  • Request / Response - Request and response objects
  • Metrics - Performance metrics
  • StreamEvent - Streaming event types
  • Error / ErrorCode - Error handling
  • Timestamps - Timestamp tracking
  • KVAllocateParams / KVHandle - KV cache management

Development

Run tests:

pytest tests/ -v

Format and lint:

ruff format .
ruff check . --fix

Type check:

mypy src/sagellm_protocol

🔄 贡献指南

请遵循以下工作流程:

  1. 创建 Issue - 描述问题/需求

    gh issue create --title "[Bug] 描述" --label "bug,sagellm-protocol"
    
  2. 开发修复 - 在本地 fix/#123-xxx 分支解决

    git checkout -b fix/#123-xxx origin/main-dev
    # 开发、测试...
    pytest -v
    ruff format . && ruff check . --fix
    
  3. 发起 PR - 提交到 main-dev 分支

    gh pr create --base main-dev --title "Fix: 描述" --body "Closes #123"
    
  4. 合并 - 审批后合并到 main-dev

更多详情见 .github/copilot-instructions.md

Documentation

For more details:

License

Proprietary - IntelliStream

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

isagellm_protocol-0.4.0.5.tar.gz (65.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

isagellm_protocol-0.4.0.5-py2.py3-none-any.whl (77.7 kB view details)

Uploaded Python 2Python 3

File details

Details for the file isagellm_protocol-0.4.0.5.tar.gz.

File metadata

  • Download URL: isagellm_protocol-0.4.0.5.tar.gz
  • Upload date:
  • Size: 65.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for isagellm_protocol-0.4.0.5.tar.gz
Algorithm Hash digest
SHA256 67bc9da45ce85ca47c927b4af2026d0c12ce4de4c114388aa200ec58d3392586
MD5 bf11b38072a1fe788757523519ec4b56
BLAKE2b-256 448b25ad3320d5c1e15ec95e00c760f2742730d5d3e6a4b90ca32a63b21f1eb3

See more details on using hashes here.

File details

Details for the file isagellm_protocol-0.4.0.5-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for isagellm_protocol-0.4.0.5-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 22c9f13b5e52c38a8c841116544fbd18dfb767bd246a3488b79b4b537603321e
MD5 d84ddf47f6d4c70c5d706657163ffb6a
BLAKE2b-256 705b6ff9a23d3884aa958e8391399012cc93f32dd2dba5a3a8f2355859170dfc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page