asepharyanaandClaude Code
e351d74fa4
Split monolithic 1012-line main.rs into layered hexagonal architecture: - Domain: entity types and LlmError enum - Application: prompt building, sampler construction, tool call parsing - Infrastructure: LlamaEngine wrapping llama-cpp-2 with isolated unsafe transmute - Presentation: Axum handlers, middleware (auth), error chain, router - Config: type-safe AppConfig with LazyLock - Bootstrap: Application struct with build() + run() Resolves build_sampler/build_sampler_params duplication. Adds simple web chat UI at GET /. Co-Authored-By: Claude Code <noreply@anthropic.com>
30 lines
646 B
TOML
30 lines
646 B
TOML
[package]
|
|
name = "llm-api"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
|
|
[dependencies]
|
|
# LLM inference
|
|
llama-cpp-2 = "0.1"
|
|
|
|
# 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"
|