Introduce predict-otron-9000: Unified server combining embeddings and inference engines. Includes OpenAI-compatible APIs, full documentation, and example scripts.

This commit is contained in:
geoffsee
2025-08-16 19:11:35 -04:00
commit 2aa6d4cdf8
28 changed files with 16595 additions and 0 deletions

View File

@@ -0,0 +1,25 @@
[package]
name = "embeddings-engine"
version = "0.1.0"
edition = "2024"
[lib]
name = "embeddings_engine"
path = "src/lib.rs"
[[bin]]
name = "embeddings-engine"
path = "src/main.rs"
[dependencies]
axum = "0.8.4"
tokio = { version = "1.45.1", features = ["full"] }
tower = "0.5.2"
serde = { version = "1.0.219", features = ["derive"] }
serde_json = "1.0.140"
fastembed = "4"
tower-http = { version = "0.6.6", features = ["trace"] }
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
rand = "0.8.5"
async-openai = "0.28.3"