Asep Haryana
6ff31b5f62
- Replaced manual prompt building with GGUF's chat template rendered through minijinja (Rust Jinja2 engine) - Simplified template: removed multi-step tool detection, reasoning extraction (not needed at template level) - Added reasoning_content separation: clean_text() returns (reasoning, answer) tuple - Added reasoning_content field to ResponseMessage and SseDelta for OpenAI-compatible output - Embedded template at build time via include_str! from templates/chat_template.jinja - Built-in support for enable_thinking, tool_definitions, tool_calls, tool_response
31 lines
662 B
TOML
31 lines
662 B
TOML
[package]
|
|
name = "llm-api"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
|
|
[dependencies]
|
|
# LLM inference
|
|
llama-cpp-2 = "0.1"
|
|
minijinja = "2"
|
|
|
|
# HTTP server
|
|
axum = { version = "0.8", features = ["json"] }
|
|
tokio = { version = "1", features = ["full"] }
|
|
tokio-stream = "0.1"
|
|
tower-http = { version = "0.6", features = ["cors", "trace"] }
|
|
|
|
# Serialization
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
|
|
# Error handling
|
|
thiserror = "1"
|
|
|
|
# Utilities
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
|
anyhow = "1"
|
|
uuid = { version = "1", features = ["v4"] }
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
futures = "0.3"
|