mirror of
https://github.com/geoffsee/predict-otron-9001.git
synced 2025-09-08 22:46:44 +00:00
predict-otron-9000 serves a leptos SSR frontend
This commit is contained in:
geoffsee
878
Cargo.lock
generated
878
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -3,7 +3,7 @@ members = [
|
||||
"crates/predict-otron-9000",
|
||||
"crates/inference-engine",
|
||||
"crates/embeddings-engine",
|
||||
"crates/leptos-chat"
|
||||
"crates/leptos-app"
|
||||
]
|
||||
default-members = ["crates/predict-otron-9000"]
|
||||
resolver = "2"
|
||||
@@ -12,6 +12,5 @@ resolver = "2"
|
||||
|
||||
[[workspace.metadata.leptos]]
|
||||
# project name
|
||||
name = "leptos-project"
|
||||
bin-package = "leptos-chat"
|
||||
lib-package = "leptos-chat"
|
||||
bin-package = "leptos-app"
|
||||
lib-package = "leptos-app"
|
||||
3
crates/leptos-app/.cargo/config.toml
Normal file
3
crates/leptos-app/.cargo/config.toml
Normal file
@@ -0,0 +1,3 @@
|
||||
# Ensure getrandom works on wasm32-unknown-unknown without needing manual RUSTFLAGS
|
||||
[target.wasm32-unknown-unknown]
|
||||
rustflags = ["--cfg", "getrandom_backend=\"wasm_js\""]
|
||||
14
crates/leptos-app/.gitignore
vendored
Normal file
14
crates/leptos-app/.gitignore
vendored
Normal file
@@ -0,0 +1,14 @@
|
||||
# Generated by Cargo
|
||||
# will have compiled files and executables
|
||||
debug/
|
||||
target/
|
||||
|
||||
# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
|
||||
# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
|
||||
Cargo.lock
|
||||
|
||||
# These are backup files generated by rustfmt
|
||||
**/*.rs.bk
|
||||
|
||||
# MSVC Windows builds of rustc generate these, which store debugging information
|
||||
*.pdb
|
||||
135
crates/leptos-app/Cargo.toml
Normal file
135
crates/leptos-app/Cargo.toml
Normal file
@@ -0,0 +1,135 @@
|
||||
[package]
|
||||
name = "leptos-app"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[lib]
|
||||
crate-type = ["cdylib", "rlib"]
|
||||
|
||||
[dependencies]
|
||||
leptos = { version = "0.8.0" }
|
||||
leptos_router = { version = "0.8.0" }
|
||||
axum = { version = "0.8.0", optional = true }
|
||||
console_error_panic_hook = { version = "0.1", optional = true }
|
||||
leptos_axum = { version = "0.8.0", optional = true }
|
||||
leptos_meta = { version = "0.8.0" }
|
||||
tokio = { version = "1", features = ["rt-multi-thread"], optional = true }
|
||||
wasm-bindgen = { version = "=0.2.100", optional = true }
|
||||
|
||||
# Chat interface dependencies
|
||||
serde = { version = "1.0", features = ["derive"] }
|
||||
serde_json = "1.0"
|
||||
async-openai-wasm = { version = "0.29", default-features = false }
|
||||
futures-util = "0.3"
|
||||
js-sys = { version = "0.3", optional = true }
|
||||
either = { version = "1.9", features = ["serde"] }
|
||||
|
||||
web-sys = { version = "0.3", optional = true, features = [
|
||||
"console",
|
||||
"Window",
|
||||
"Document",
|
||||
"Element",
|
||||
"HtmlElement",
|
||||
"HtmlInputElement",
|
||||
"HtmlSelectElement",
|
||||
"HtmlTextAreaElement",
|
||||
"Event",
|
||||
"EventTarget",
|
||||
"KeyboardEvent",
|
||||
] }
|
||||
|
||||
[dependencies.uuid]
|
||||
version = "1.0"
|
||||
features = [
|
||||
"v4",
|
||||
"fast-rng",
|
||||
"macro-diagnostics",
|
||||
"js",
|
||||
]
|
||||
|
||||
[features]
|
||||
hydrate = [
|
||||
"leptos/hydrate",
|
||||
"dep:console_error_panic_hook",
|
||||
"dep:wasm-bindgen",
|
||||
"dep:js-sys",
|
||||
"dep:web-sys",
|
||||
]
|
||||
ssr = [
|
||||
"dep:axum",
|
||||
"dep:tokio",
|
||||
"dep:leptos_axum",
|
||||
"leptos/ssr",
|
||||
"leptos_meta/ssr",
|
||||
"leptos_router/ssr",
|
||||
]
|
||||
|
||||
# Defines a size-optimized profile for the WASM bundle in release mode
|
||||
[profile.wasm-release]
|
||||
inherits = "release"
|
||||
opt-level = 'z'
|
||||
lto = true
|
||||
codegen-units = 1
|
||||
panic = "abort"
|
||||
|
||||
[package.metadata.leptos]
|
||||
# The name used by wasm-bindgen/cargo-leptos for the JS/WASM bundle. Defaults to the crate name
|
||||
output-name = "leptos-app"
|
||||
|
||||
# The site root folder is where cargo-leptos generate all output. WARNING: all content of this folder will be erased on a rebuild. Use it in your server setup.
|
||||
site-root = "target/site"
|
||||
|
||||
# The site-root relative folder where all compiled output (JS, WASM and CSS) is written
|
||||
# Defaults to pkg
|
||||
site-pkg-dir = "pkg"
|
||||
|
||||
# [Optional] The source CSS file. If it ends with .sass or .scss then it will be compiled by dart-sass into CSS. The CSS is optimized by Lightning CSS before being written to <site-root>/<site-pkg>/app.css
|
||||
style-file = "style/main.scss"
|
||||
# Assets source dir. All files found here will be copied and synchronized to site-root.
|
||||
# The assets-dir cannot have a sub directory with the same name/path as site-pkg-dir.
|
||||
#
|
||||
# Optional. Env: LEPTOS_ASSETS_DIR.
|
||||
assets-dir = "public"
|
||||
|
||||
# The IP and port (ex: 127.0.0.1:3000) where the server serves the content. Use it in your server setup.
|
||||
site-addr = "127.0.0.1:3000"
|
||||
|
||||
# The port to use for automatic reload monitoring
|
||||
reload-port = 3001
|
||||
|
||||
# [Optional] Command to use when running end2end tests. It will run in the end2end dir.
|
||||
# [Windows] for non-WSL use "npx.cmd playwright test"
|
||||
# This binary name can be checked in Powershell with Get-Command npx
|
||||
end2end-cmd = "npx playwright test"
|
||||
end2end-dir = "end2end"
|
||||
|
||||
# The browserlist query used for optimizing the CSS.
|
||||
browserquery = "defaults"
|
||||
|
||||
# The environment Leptos will run in, usually either "DEV" or "PROD"
|
||||
env = "DEV"
|
||||
|
||||
# The features to use when compiling the bin target
|
||||
#
|
||||
# Optional. Can be over-ridden with the command line parameter --bin-features
|
||||
bin-features = ["ssr"]
|
||||
|
||||
# If the --no-default-features flag should be used when compiling the bin target
|
||||
#
|
||||
# Optional. Defaults to false.
|
||||
bin-default-features = false
|
||||
|
||||
# The features to use when compiling the lib target
|
||||
#
|
||||
# Optional. Can be over-ridden with the command line parameter --lib-features
|
||||
lib-features = ["hydrate"]
|
||||
|
||||
# If the --no-default-features flag should be used when compiling the lib target
|
||||
#
|
||||
# Optional. Defaults to false.
|
||||
lib-default-features = false
|
||||
|
||||
# The profile to use for the lib target when compiling for release
|
||||
#
|
||||
# Optional. Defaults to "release".
|
||||
lib-profile-release = "wasm-release"
|
||||
21
crates/leptos-app/Dockerfile
Normal file
21
crates/leptos-app/Dockerfile
Normal file
@@ -0,0 +1,21 @@
|
||||
# Build stage
|
||||
FROM rust:1-alpine AS builder
|
||||
|
||||
# Install build dependencies
|
||||
RUN apk add --no-cache npm nodejs musl-dev pkgconfig openssl-dev git curl bash
|
||||
|
||||
RUN curl -L --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/cargo-bins/cargo-binstall/main/install-from-binstall-release.sh | bash
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Copy manifest first (cache deps)
|
||||
COPY . .
|
||||
|
||||
# Install cargo-leptos
|
||||
RUN cargo binstall cargo-leptos
|
||||
|
||||
# Build release artifacts
|
||||
RUN cargo leptos build --release
|
||||
|
||||
EXPOSE 8788
|
||||
CMD ["cargo", "leptos", "serve", "--release"]
|
||||
3
crates/leptos-app/end2end/.gitignore
vendored
Normal file
3
crates/leptos-app/end2end/.gitignore
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
node_modules
|
||||
playwright-report
|
||||
test-results
|
||||
15
crates/leptos-app/end2end/package.json
Normal file
15
crates/leptos-app/end2end/package.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"name": "end2end",
|
||||
"version": "1.0.0",
|
||||
"description": "",
|
||||
"main": "index.js",
|
||||
"scripts": {},
|
||||
"keywords": [],
|
||||
"author": "",
|
||||
"license": "ISC",
|
||||
"devDependencies": {
|
||||
"@playwright/test": "^1.44.1",
|
||||
"@types/node": "^20.12.12",
|
||||
"typescript": "^5.4.5"
|
||||
}
|
||||
}
|
||||
105
crates/leptos-app/end2end/playwright.config.ts
Normal file
105
crates/leptos-app/end2end/playwright.config.ts
Normal file
@@ -0,0 +1,105 @@
|
||||
import type { PlaywrightTestConfig } from "@playwright/test";
|
||||
import { devices, defineConfig } from "@playwright/test";
|
||||
|
||||
/**
|
||||
* Read environment variables from file.
|
||||
* https://github.com/motdotla/dotenv
|
||||
*/
|
||||
// require('dotenv').config();
|
||||
|
||||
/**
|
||||
* See https://playwright.dev/docs/test-configuration.
|
||||
*/
|
||||
export default defineConfig({
|
||||
testDir: "./tests",
|
||||
/* Maximum time one test can run for. */
|
||||
timeout: 30 * 1000,
|
||||
expect: {
|
||||
/**
|
||||
* Maximum time expect() should wait for the condition to be met.
|
||||
* For example in `await expect(locator).toHaveText();`
|
||||
*/
|
||||
timeout: 5000,
|
||||
},
|
||||
/* Run tests in files in parallel */
|
||||
fullyParallel: true,
|
||||
/* Fail the build on CI if you accidentally left test.only in the source code. */
|
||||
forbidOnly: !!process.env.CI,
|
||||
/* Retry on CI only */
|
||||
retries: process.env.CI ? 2 : 0,
|
||||
/* Opt out of parallel tests on CI. */
|
||||
workers: process.env.CI ? 1 : undefined,
|
||||
/* Reporter to use. See https://playwright.dev/docs/test-reporters */
|
||||
reporter: "html",
|
||||
/* Shared settings for all the projects below. See https://playwright.dev/docs/api/class-testoptions. */
|
||||
use: {
|
||||
/* Maximum time each action such as `click()` can take. Defaults to 0 (no limit). */
|
||||
actionTimeout: 0,
|
||||
/* Base URL to use in actions like `await page.goto('/')`. */
|
||||
// baseURL: 'http://localhost:3000',
|
||||
|
||||
/* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
|
||||
trace: "on-first-retry",
|
||||
},
|
||||
|
||||
/* Configure projects for major browsers */
|
||||
projects: [
|
||||
{
|
||||
name: "chromium",
|
||||
use: {
|
||||
...devices["Desktop Chrome"],
|
||||
},
|
||||
},
|
||||
|
||||
{
|
||||
name: "firefox",
|
||||
use: {
|
||||
...devices["Desktop Firefox"],
|
||||
},
|
||||
},
|
||||
|
||||
{
|
||||
name: "webkit",
|
||||
use: {
|
||||
...devices["Desktop Safari"],
|
||||
},
|
||||
},
|
||||
|
||||
/* Test against mobile viewports. */
|
||||
// {
|
||||
// name: 'Mobile Chrome',
|
||||
// use: {
|
||||
// ...devices['Pixel 5'],
|
||||
// },
|
||||
// },
|
||||
// {
|
||||
// name: 'Mobile Safari',
|
||||
// use: {
|
||||
// ...devices['iPhone 12'],
|
||||
// },
|
||||
// },
|
||||
|
||||
/* Test against branded browsers. */
|
||||
// {
|
||||
// name: 'Microsoft Edge',
|
||||
// use: {
|
||||
// channel: 'msedge',
|
||||
// },
|
||||
// },
|
||||
// {
|
||||
// name: 'Google Chrome',
|
||||
// use: {
|
||||
// channel: 'chrome',
|
||||
// },
|
||||
// },
|
||||
],
|
||||
|
||||
/* Folder for test artifacts such as screenshots, videos, traces, etc. */
|
||||
// outputDir: 'test-results/',
|
||||
|
||||
/* Run your local dev server before starting the tests */
|
||||
// webServer: {
|
||||
// command: 'npm run start',
|
||||
// port: 3000,
|
||||
// },
|
||||
});
|
||||
9
crates/leptos-app/end2end/tests/example.spec.ts
Normal file
9
crates/leptos-app/end2end/tests/example.spec.ts
Normal file
@@ -0,0 +1,9 @@
|
||||
import { test, expect } from "@playwright/test";
|
||||
|
||||
test("homepage has title and heading text", async ({ page }) => {
|
||||
await page.goto("http://localhost:3000/");
|
||||
|
||||
await expect(page).toHaveTitle("Welcome to Leptos");
|
||||
|
||||
await expect(page.locator("h1")).toHaveText("Welcome to Leptos!");
|
||||
});
|
||||
109
crates/leptos-app/end2end/tsconfig.json
Normal file
109
crates/leptos-app/end2end/tsconfig.json
Normal file
@@ -0,0 +1,109 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
/* Visit https://aka.ms/tsconfig to read more about this file */
|
||||
|
||||
/* Projects */
|
||||
// "incremental": true, /* Save .tsbuildinfo files to allow for incremental compilation of projects. */
|
||||
// "composite": true, /* Enable constraints that allow a TypeScript project to be used with project references. */
|
||||
// "tsBuildInfoFile": "./.tsbuildinfo", /* Specify the path to .tsbuildinfo incremental compilation file. */
|
||||
// "disableSourceOfProjectReferenceRedirect": true, /* Disable preferring source files instead of declaration files when referencing composite projects. */
|
||||
// "disableSolutionSearching": true, /* Opt a project out of multi-project reference checking when editing. */
|
||||
// "disableReferencedProjectLoad": true, /* Reduce the number of projects loaded automatically by TypeScript. */
|
||||
|
||||
/* Language and Environment */
|
||||
"target": "es2016", /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
|
||||
// "lib": [], /* Specify a set of bundled library declaration files that describe the target runtime environment. */
|
||||
// "jsx": "preserve", /* Specify what JSX code is generated. */
|
||||
// "experimentalDecorators": true, /* Enable experimental support for legacy experimental decorators. */
|
||||
// "emitDecoratorMetadata": true, /* Emit design-type metadata for decorated declarations in source files. */
|
||||
// "jsxFactory": "", /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h'. */
|
||||
// "jsxFragmentFactory": "", /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
|
||||
// "jsxImportSource": "", /* Specify module specifier used to import the JSX factory functions when using 'jsx: react-jsx*'. */
|
||||
// "reactNamespace": "", /* Specify the object invoked for 'createElement'. This only applies when targeting 'react' JSX emit. */
|
||||
// "noLib": true, /* Disable including any library files, including the default lib.d.ts. */
|
||||
// "useDefineForClassFields": true, /* Emit ECMAScript-standard-compliant class fields. */
|
||||
// "moduleDetection": "auto", /* Control what method is used to detect module-format JS files. */
|
||||
|
||||
/* Modules */
|
||||
"module": "commonjs", /* Specify what module code is generated. */
|
||||
// "rootDir": "./", /* Specify the root folder within your source files. */
|
||||
// "moduleResolution": "node10", /* Specify how TypeScript looks up a file from a given module specifier. */
|
||||
// "baseUrl": "./", /* Specify the base directory to resolve non-relative module names. */
|
||||
// "paths": {}, /* Specify a set of entries that re-map imports to additional lookup locations. */
|
||||
// "rootDirs": [], /* Allow multiple folders to be treated as one when resolving modules. */
|
||||
// "typeRoots": [], /* Specify multiple folders that act like './node_modules/@types'. */
|
||||
// "types": [], /* Specify type package names to be included without being referenced in a source file. */
|
||||
// "allowUmdGlobalAccess": true, /* Allow accessing UMD globals from modules. */
|
||||
// "moduleSuffixes": [], /* List of file name suffixes to search when resolving a module. */
|
||||
// "allowImportingTsExtensions": true, /* Allow imports to include TypeScript file extensions. Requires '--moduleResolution bundler' and either '--noEmit' or '--emitDeclarationOnly' to be set. */
|
||||
// "resolvePackageJsonExports": true, /* Use the package.json 'exports' field when resolving package imports. */
|
||||
// "resolvePackageJsonImports": true, /* Use the package.json 'imports' field when resolving imports. */
|
||||
// "customConditions": [], /* Conditions to set in addition to the resolver-specific defaults when resolving imports. */
|
||||
// "resolveJsonModule": true, /* Enable importing .json files. */
|
||||
// "allowArbitraryExtensions": true, /* Enable importing files with any extension, provided a declaration file is present. */
|
||||
// "noResolve": true, /* Disallow 'import's, 'require's or '<reference>'s from expanding the number of files TypeScript should add to a project. */
|
||||
|
||||
/* JavaScript Support */
|
||||
// "allowJs": true, /* Allow JavaScript files to be a part of your program. Use the 'checkJS' option to get errors from these files. */
|
||||
// "checkJs": true, /* Enable error reporting in type-checked JavaScript files. */
|
||||
// "maxNodeModuleJsDepth": 1, /* Specify the maximum folder depth used for checking JavaScript files from 'node_modules'. Only applicable with 'allowJs'. */
|
||||
|
||||
/* Emit */
|
||||
// "declaration": true, /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
|
||||
// "declarationMap": true, /* Create sourcemaps for d.ts files. */
|
||||
// "emitDeclarationOnly": true, /* Only output d.ts files and not JavaScript files. */
|
||||
// "sourceMap": true, /* Create source map files for emitted JavaScript files. */
|
||||
// "inlineSourceMap": true, /* Include sourcemap files inside the emitted JavaScript. */
|
||||
// "outFile": "./", /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
|
||||
// "outDir": "./", /* Specify an output folder for all emitted files. */
|
||||
// "removeComments": true, /* Disable emitting comments. */
|
||||
// "noEmit": true, /* Disable emitting files from a compilation. */
|
||||
// "importHelpers": true, /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
|
||||
// "importsNotUsedAsValues": "remove", /* Specify emit/checking behavior for imports that are only used for types. */
|
||||
// "downlevelIteration": true, /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
|
||||
// "sourceRoot": "", /* Specify the root path for debuggers to find the reference source code. */
|
||||
// "mapRoot": "", /* Specify the location where debugger should locate map files instead of generated locations. */
|
||||
// "inlineSources": true, /* Include source code in the sourcemaps inside the emitted JavaScript. */
|
||||
// "emitBOM": true, /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
|
||||
// "newLine": "crlf", /* Set the newline character for emitting files. */
|
||||
// "stripInternal": true, /* Disable emitting declarations that have '@internal' in their JSDoc comments. */
|
||||
// "noEmitHelpers": true, /* Disable generating custom helper functions like '__extends' in compiled output. */
|
||||
// "noEmitOnError": true, /* Disable emitting files if any type checking errors are reported. */
|
||||
// "preserveConstEnums": true, /* Disable erasing 'const enum' declarations in generated code. */
|
||||
// "declarationDir": "./", /* Specify the output directory for generated declaration files. */
|
||||
// "preserveValueImports": true, /* Preserve unused imported values in the JavaScript output that would otherwise be removed. */
|
||||
|
||||
/* Interop Constraints */
|
||||
// "isolatedModules": true, /* Ensure that each file can be safely transpiled without relying on other imports. */
|
||||
// "verbatimModuleSyntax": true, /* Do not transform or elide any imports or exports not marked as type-only, ensuring they are written in the output file's format based on the 'module' setting. */
|
||||
// "allowSyntheticDefaultImports": true, /* Allow 'import x from y' when a module doesn't have a default export. */
|
||||
"esModuleInterop": true, /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables 'allowSyntheticDefaultImports' for type compatibility. */
|
||||
// "preserveSymlinks": true, /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
|
||||
"forceConsistentCasingInFileNames": true, /* Ensure that casing is correct in imports. */
|
||||
|
||||
/* Type Checking */
|
||||
"strict": true, /* Enable all strict type-checking options. */
|
||||
// "noImplicitAny": true, /* Enable error reporting for expressions and declarations with an implied 'any' type. */
|
||||
// "strictNullChecks": true, /* When type checking, take into account 'null' and 'undefined'. */
|
||||
// "strictFunctionTypes": true, /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
|
||||
// "strictBindCallApply": true, /* Check that the arguments for 'bind', 'call', and 'apply' methods match the original function. */
|
||||
// "strictPropertyInitialization": true, /* Check for class properties that are declared but not set in the constructor. */
|
||||
// "noImplicitThis": true, /* Enable error reporting when 'this' is given the type 'any'. */
|
||||
// "useUnknownInCatchVariables": true, /* Default catch clause variables as 'unknown' instead of 'any'. */
|
||||
// "alwaysStrict": true, /* Ensure 'use strict' is always emitted. */
|
||||
// "noUnusedLocals": true, /* Enable error reporting when local variables aren't read. */
|
||||
// "noUnusedParameters": true, /* Raise an error when a function parameter isn't read. */
|
||||
// "exactOptionalPropertyTypes": true, /* Interpret optional property types as written, rather than adding 'undefined'. */
|
||||
// "noImplicitReturns": true, /* Enable error reporting for codepaths that do not explicitly return in a function. */
|
||||
// "noFallthroughCasesInSwitch": true, /* Enable error reporting for fallthrough cases in switch statements. */
|
||||
// "noUncheckedIndexedAccess": true, /* Add 'undefined' to a type when accessed using an index. */
|
||||
// "noImplicitOverride": true, /* Ensure overriding members in derived classes are marked with an override modifier. */
|
||||
// "noPropertyAccessFromIndexSignature": true, /* Enforces using indexed accessors for keys declared using an indexed type. */
|
||||
// "allowUnusedLabels": true, /* Disable error reporting for unused labels. */
|
||||
// "allowUnreachableCode": true, /* Disable error reporting for unreachable code. */
|
||||
|
||||
/* Completeness */
|
||||
// "skipDefaultLibCheck": true, /* Skip type checking .d.ts files that are included with TypeScript. */
|
||||
"skipLibCheck": true /* Skip type checking all .d.ts files. */
|
||||
}
|
||||
}
|
||||
BIN
crates/leptos-app/public/favicon.ico
Normal file
BIN
crates/leptos-app/public/favicon.ico
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 15 KiB |
@@ -1,12 +1,23 @@
|
||||
use leptos::*;
|
||||
use leptos_meta::*;
|
||||
use leptos_router::*;
|
||||
use leptos::prelude::*;
|
||||
use leptos_meta::{provide_meta_context, MetaTags, Stylesheet, Title};
|
||||
use leptos_router::{
|
||||
components::{Route, Router, Routes},
|
||||
StaticSegment,
|
||||
};
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
use serde::{Deserialize, Serialize};
|
||||
#[cfg(feature = "hydrate")]
|
||||
use std::collections::VecDeque;
|
||||
#[cfg(feature = "hydrate")]
|
||||
use uuid::Uuid;
|
||||
#[cfg(feature = "hydrate")]
|
||||
use js_sys::Date;
|
||||
#[cfg(feature = "hydrate")]
|
||||
use web_sys::{HtmlInputElement, KeyboardEvent, SubmitEvent};
|
||||
#[cfg(feature = "hydrate")]
|
||||
use futures_util::StreamExt;
|
||||
#[cfg(feature = "hydrate")]
|
||||
use async_openai_wasm::{
|
||||
types::{
|
||||
ChatCompletionRequestAssistantMessageArgs, ChatCompletionRequestSystemMessageArgs,
|
||||
@@ -14,9 +25,14 @@ use async_openai_wasm::{
|
||||
},
|
||||
Client,
|
||||
};
|
||||
#[cfg(feature = "hydrate")]
|
||||
use async_openai_wasm::config::OpenAIConfig;
|
||||
use async_openai_wasm::types::{ChatCompletionResponseStream, Model, Role, FinishReason};
|
||||
#[cfg(feature = "hydrate")]
|
||||
use async_openai_wasm::types::{Role, FinishReason};
|
||||
#[cfg(feature = "hydrate")]
|
||||
use leptos::task::spawn_local;
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Message {
|
||||
pub id: String,
|
||||
@@ -25,12 +41,15 @@ pub struct Message {
|
||||
pub timestamp: f64,
|
||||
}
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct MessageContent(pub either::Either<String, Vec<std::collections::HashMap<String, MessageInnerContent>>>);
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct MessageInnerContent(pub either::Either<String, std::collections::HashMap<String, String>>);
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ChatMessage {
|
||||
pub role: String,
|
||||
@@ -38,59 +57,12 @@ pub struct ChatMessage {
|
||||
pub name: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ChatRequest {
|
||||
pub model: String,
|
||||
pub messages: Vec<ChatMessage>,
|
||||
pub max_tokens: Option<usize>,
|
||||
pub temperature: Option<f64>,
|
||||
pub top_p: Option<f64>,
|
||||
pub stream: Option<bool>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ChatResponse {
|
||||
pub id: String,
|
||||
pub object: String,
|
||||
pub created: u64,
|
||||
pub model: String,
|
||||
pub choices: Vec<Choice>,
|
||||
pub usage: Usage,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Choice {
|
||||
pub index: usize,
|
||||
pub message: ChatMessage,
|
||||
pub finish_reason: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Usage {
|
||||
pub prompt_tokens: usize,
|
||||
pub completion_tokens: usize,
|
||||
pub total_tokens: usize,
|
||||
}
|
||||
|
||||
#[component]
|
||||
pub fn App() -> impl IntoView {
|
||||
provide_meta_context();
|
||||
|
||||
view! {
|
||||
<Stylesheet id="leptos" href="/style/main.css"/>
|
||||
<Title text="Chat Interface"/>
|
||||
<Router>
|
||||
<main>
|
||||
<Routes>
|
||||
<Route path="/" view=ChatInterface/>
|
||||
</Routes>
|
||||
</main>
|
||||
</Router>
|
||||
}
|
||||
}
|
||||
#[cfg(feature = "hydrate")]
|
||||
const DEFAULT_MODEL: &str = "default";
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
async fn fetch_available_models() -> Result<Vec<OpenAIModel>, String> {
|
||||
log::info!("[DEBUG_LOG] fetch_available_models: Starting model fetch from http://localhost:8080/v1");
|
||||
leptos::logging::log!("[DEBUG_LOG] fetch_available_models: Starting model fetch from http://localhost:8080/v1");
|
||||
|
||||
let config = OpenAIConfig::new().with_api_base("http://localhost:8080/v1".to_string());
|
||||
let client = Client::with_config(config);
|
||||
@@ -98,126 +70,110 @@ async fn fetch_available_models() -> Result<Vec<OpenAIModel>, String> {
|
||||
match client.models().list().await {
|
||||
Ok(response) => {
|
||||
let model_count = response.data.len();
|
||||
log::info!("[DEBUG_LOG] fetch_available_models: Successfully fetched {} models", model_count);
|
||||
leptos::logging::log!("[DEBUG_LOG] fetch_available_models: Successfully fetched {} models", model_count);
|
||||
|
||||
if model_count > 0 {
|
||||
let model_names: Vec<String> = response.data.iter().map(|m| m.id.clone()).collect();
|
||||
log::debug!("[DEBUG_LOG] fetch_available_models: Available models: {:?}", model_names);
|
||||
leptos::logging::log!("[DEBUG_LOG] fetch_available_models: Available models: {:?}", model_names);
|
||||
} else {
|
||||
log::warn!("[DEBUG_LOG] fetch_available_models: No models returned by server");
|
||||
leptos::logging::log!("[DEBUG_LOG] fetch_available_models: No models returned by server");
|
||||
}
|
||||
|
||||
Ok(response.data)
|
||||
},
|
||||
Err(e) => {
|
||||
log::error!("[DEBUG_LOG] fetch_available_models: Failed to fetch models: {:?}", e);
|
||||
|
||||
let error_details = format!("{:?}", e);
|
||||
if error_details.contains("400") || error_details.contains("Bad Request") {
|
||||
log::error!("[DEBUG_LOG] fetch_available_models: HTTP 400 - Server rejected models request");
|
||||
} else if error_details.contains("404") || error_details.contains("Not Found") {
|
||||
log::error!("[DEBUG_LOG] fetch_available_models: HTTP 404 - Models endpoint not found");
|
||||
} else if error_details.contains("Connection") || error_details.contains("connection") {
|
||||
log::error!("[DEBUG_LOG] fetch_available_models: Connection error - server may be down");
|
||||
}
|
||||
|
||||
leptos::logging::log!("[DEBUG_LOG] fetch_available_models: Failed to fetch models: {:?}", e);
|
||||
Err(format!("Failed to fetch models: {}", e))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn send_chat_request(chat_request: ChatRequest) -> ChatCompletionResponseStream {
|
||||
let config = OpenAIConfig::new().with_api_base("http://localhost:8080/v1".to_string());
|
||||
let client = Client::with_config(config);
|
||||
|
||||
let mut typed_chat = async_openai_wasm::types::CreateChatCompletionRequest {
|
||||
messages: vec![],
|
||||
model: "".to_string(),
|
||||
store: None,
|
||||
reasoning_effort: None,
|
||||
metadata: None,
|
||||
frequency_penalty: None,
|
||||
logit_bias: None,
|
||||
logprobs: None,
|
||||
top_logprobs: None,
|
||||
max_tokens: None,
|
||||
max_completion_tokens: None,
|
||||
n: None,
|
||||
modalities: None,
|
||||
prediction: None,
|
||||
audio: None,
|
||||
presence_penalty: None,
|
||||
response_format: None,
|
||||
seed: None,
|
||||
service_tier: None,
|
||||
stop: None,
|
||||
stream: None,
|
||||
stream_options: None,
|
||||
temperature: None,
|
||||
top_p: None,
|
||||
tools: None,
|
||||
tool_choice: None,
|
||||
parallel_tool_calls: None,
|
||||
user: None,
|
||||
function_call: None,
|
||||
functions: None,
|
||||
web_search_options: None,
|
||||
extra_params: None,
|
||||
};
|
||||
|
||||
typed_chat.messages = chat_request.messages
|
||||
.iter()
|
||||
.map(|msg| {
|
||||
let content = match &msg.content {
|
||||
Some(MessageContent(either::Either::Left(text))) => text.clone(),
|
||||
_ => "".to_string()
|
||||
};
|
||||
let role = msg.role.clone();
|
||||
match role.as_str() {
|
||||
"system" => ChatCompletionRequestSystemMessageArgs::default()
|
||||
.content(content)
|
||||
.build()
|
||||
.expect("failed to build system message")
|
||||
.into(),
|
||||
"user" => ChatCompletionRequestUserMessageArgs::default()
|
||||
.content(content)
|
||||
.build()
|
||||
.expect("failed to build user message")
|
||||
.into(),
|
||||
"assistant" => ChatCompletionRequestAssistantMessageArgs::default()
|
||||
.content(content)
|
||||
.build()
|
||||
.expect("failed to build assistant message")
|
||||
.into(),
|
||||
_ => ChatCompletionRequestUserMessageArgs::default()
|
||||
.content(content)
|
||||
.build()
|
||||
.expect("failed to build default message")
|
||||
.into()
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
client.chat().create_stream(typed_chat).await.unwrap()
|
||||
pub fn shell(options: LeptosOptions) -> impl IntoView {
|
||||
view! {
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8"/>
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||||
<AutoReload options=options.clone() />
|
||||
<HydrationScripts options/>
|
||||
<MetaTags/>
|
||||
</head>
|
||||
<body>
|
||||
<App/>
|
||||
</body>
|
||||
</html>
|
||||
}
|
||||
}
|
||||
|
||||
// #[cfg(not(target_arch = "wasm32"))]
|
||||
// async fn send_chat_request(_chat_request: ChatRequest) -> Result<ChatResponse, String> {
|
||||
// Err("leptos-chat chat request only supported on wasm32 target".to_string())
|
||||
// }
|
||||
#[component]
|
||||
pub fn App() -> impl IntoView {
|
||||
// Provides context that manages stylesheets, titles, meta tags, etc.
|
||||
provide_meta_context();
|
||||
|
||||
const DEFAULT_MODEL: &str = "default";
|
||||
view! {
|
||||
// injects a stylesheet into the document <head>
|
||||
// id=leptos means cargo-leptos will hot-reload this stylesheet
|
||||
<Stylesheet id="leptos" href="/pkg/leptos-app.css"/>
|
||||
|
||||
// sets the document title
|
||||
<Title text="Chat Interface"/>
|
||||
|
||||
// content for this chat interface
|
||||
<Router>
|
||||
<main>
|
||||
<Routes fallback=|| "Page not found.".into_view()>
|
||||
<Route path=StaticSegment("") view=ChatInterface/>
|
||||
</Routes>
|
||||
</main>
|
||||
</Router>
|
||||
}
|
||||
}
|
||||
|
||||
/// Renders the home page of your application.
|
||||
#[component]
|
||||
fn HomePage() -> impl IntoView {
|
||||
// Creates a reactive value to update the button
|
||||
let count = RwSignal::new(0);
|
||||
let on_click = move |_| *count.write() += 1;
|
||||
|
||||
view! {
|
||||
<h1>"Welcome to Leptos!"</h1>
|
||||
<button on:click=on_click>"Click Me: " {count}</button>
|
||||
}
|
||||
}
|
||||
|
||||
/// Renders the chat interface
|
||||
#[component]
|
||||
fn ChatInterface() -> impl IntoView {
|
||||
let (messages, set_messages) = create_signal::<VecDeque<Message>>(VecDeque::new());
|
||||
let (input_value, set_input_value) = create_signal(String::new());
|
||||
let (is_loading, set_is_loading) = create_signal(false);
|
||||
let (available_models, set_available_models) = create_signal::<Vec<OpenAIModel>>(Vec::new());
|
||||
let (selected_model, set_selected_model) = create_signal(DEFAULT_MODEL.to_string());
|
||||
let (models_loading, set_models_loading) = create_signal(false);
|
||||
#[cfg(feature = "hydrate")]
|
||||
{
|
||||
ChatInterfaceImpl()
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "hydrate"))]
|
||||
{
|
||||
view! {
|
||||
<div class="chat-container">
|
||||
<h1>"Chat Interface"</h1>
|
||||
<p>"Loading chat interface..."</p>
|
||||
</div>
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[component]
|
||||
fn ChatInterfaceImpl() -> impl IntoView {
|
||||
let (messages, set_messages) = RwSignal::new(VecDeque::<Message>::new()).split();
|
||||
let (input_value, set_input_value) = RwSignal::new(String::new()).split();
|
||||
let (is_loading, set_is_loading) = RwSignal::new(false).split();
|
||||
let (available_models, set_available_models) = RwSignal::new(Vec::<OpenAIModel>::new()).split();
|
||||
let (selected_model, set_selected_model) = RwSignal::new(DEFAULT_MODEL.to_string()).split();
|
||||
let (models_loading, set_models_loading) = RwSignal::new(false).split();
|
||||
|
||||
// Fetch models on component initialization
|
||||
create_effect(move |_| {
|
||||
Effect::new(move |_| {
|
||||
spawn_local(async move {
|
||||
set_models_loading.set(true);
|
||||
match fetch_available_models().await {
|
||||
@@ -226,8 +182,7 @@ fn ChatInterface() -> impl IntoView {
|
||||
set_models_loading.set(false);
|
||||
}
|
||||
Err(e) => {
|
||||
log::error!("Failed to fetch models: {}", e);
|
||||
// Set a default model if fetching fails
|
||||
leptos::logging::log!("Failed to fetch models: {}", e);
|
||||
set_available_models.set(vec![]);
|
||||
set_models_loading.set(false);
|
||||
}
|
||||
@@ -235,17 +190,15 @@ fn ChatInterface() -> impl IntoView {
|
||||
});
|
||||
});
|
||||
|
||||
let send_message = create_action(move |content: &String| {
|
||||
let send_message = Action::new_unsync(move |content: &String| {
|
||||
let content = content.clone();
|
||||
async move {
|
||||
if content.trim().is_empty() {
|
||||
log::debug!("[DEBUG_LOG] send_message: Empty content, skipping");
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Empty content, skipping");
|
||||
return;
|
||||
}
|
||||
|
||||
log::info!("[DEBUG_LOG] send_message: Starting message send process");
|
||||
log::debug!("[DEBUG_LOG] send_message: User message content length: {}", content.len());
|
||||
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Starting message send process");
|
||||
set_is_loading.set(true);
|
||||
|
||||
// Add user message to chat
|
||||
@@ -269,43 +222,26 @@ fn ChatInterface() -> impl IntoView {
|
||||
chat_messages.push(system_message.into());
|
||||
|
||||
// Add history messages
|
||||
let history_count = messages.with_untracked(|msgs| {
|
||||
let count = msgs.len();
|
||||
for msg in msgs.iter() {
|
||||
match msg.role.as_str() {
|
||||
"user" => {
|
||||
let message = ChatCompletionRequestUserMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build user message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
"assistant" => {
|
||||
let message = ChatCompletionRequestAssistantMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build assistant message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
"system" => {
|
||||
let message = ChatCompletionRequestSystemMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build system message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
_ => {
|
||||
// Default to user message for unknown roles
|
||||
let message = ChatCompletionRequestUserMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build default message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
let history_count = messages.get_untracked().len();
|
||||
for msg in messages.get_untracked().iter() {
|
||||
match msg.role.as_str() {
|
||||
"user" => {
|
||||
let message = ChatCompletionRequestUserMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build user message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
"assistant" => {
|
||||
let message = ChatCompletionRequestAssistantMessageArgs::default()
|
||||
.content(msg.content.clone())
|
||||
.build()
|
||||
.expect("failed to build assistant message");
|
||||
chat_messages.push(message.into());
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
count
|
||||
});
|
||||
}
|
||||
|
||||
// Add current user message
|
||||
let message = ChatCompletionRequestUserMessageArgs::default()
|
||||
@@ -317,45 +253,36 @@ fn ChatInterface() -> impl IntoView {
|
||||
let current_model = selected_model.get_untracked();
|
||||
let total_messages = chat_messages.len();
|
||||
|
||||
log::info!("[DEBUG_LOG] send_message: Preparing request - model: '{}', history_count: {}, total_messages: {}",
|
||||
current_model, history_count, total_messages);
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Preparing request - model: '{}', history_count: {}, total_messages: {}",
|
||||
current_model, history_count, total_messages);
|
||||
|
||||
let request = CreateChatCompletionRequestArgs::default()
|
||||
.model(current_model.as_str())
|
||||
.max_tokens(512u32)
|
||||
.messages(chat_messages)
|
||||
.stream(true) // ensure server streams
|
||||
.stream(true)
|
||||
.build()
|
||||
.expect("failed to build request");
|
||||
|
||||
// Log request details for debugging server issues
|
||||
log::info!("[DEBUG_LOG] send_message: Request configuration - model: '{}', max_tokens: 512, stream: true, messages_count: {}",
|
||||
current_model, total_messages);
|
||||
log::debug!("[DEBUG_LOG] send_message: Request details - history_messages: {}, system_messages: 1, user_messages: {}",
|
||||
history_count, total_messages - history_count - 1);
|
||||
|
||||
// Send request
|
||||
let config = OpenAIConfig::new().with_api_base("http://localhost:8080/v1".to_string());
|
||||
let client = Client::with_config(config);
|
||||
|
||||
log::info!("[DEBUG_LOG] send_message: Sending request to http://localhost:8080/v1 with model: '{}'", current_model);
|
||||
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Sending request to http://localhost:8080/v1 with model: '{}'", current_model);
|
||||
|
||||
match client.chat().create_stream(request).await {
|
||||
Ok(mut stream) => {
|
||||
log::info!("[DEBUG_LOG] send_message: Successfully created stream, starting to receive response");
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Successfully created stream");
|
||||
|
||||
// Defer creating assistant message until we receive role=assistant from the stream
|
||||
let mut assistant_created = false;
|
||||
let mut content_appended = false;
|
||||
let mut chunks_received = 0;
|
||||
// Stream loop: handle deltas and finish events
|
||||
|
||||
while let Some(next) = stream.next().await {
|
||||
match next {
|
||||
Ok(chunk) => {
|
||||
chunks_received += 1;
|
||||
if let Some(choice) = chunk.choices.get(0) {
|
||||
// 1) Create assistant message when role arrives
|
||||
if !assistant_created {
|
||||
if let Some(role) = &choice.delta.role {
|
||||
if role == &Role::Assistant {
|
||||
@@ -373,10 +300,8 @@ fn ChatInterface() -> impl IntoView {
|
||||
}
|
||||
}
|
||||
|
||||
// 2) Append content tokens when provided
|
||||
if let Some(content) = &choice.delta.content {
|
||||
if !content.is_empty() {
|
||||
// If content arrives before role, create assistant message now
|
||||
if !assistant_created {
|
||||
assistant_created = true;
|
||||
let assistant_id = Uuid::new_v4().to_string();
|
||||
@@ -401,23 +326,21 @@ fn ChatInterface() -> impl IntoView {
|
||||
}
|
||||
}
|
||||
|
||||
// 3) Stop on finish_reason=="stop" (mirrors [DONE])
|
||||
if let Some(reason) = &choice.finish_reason {
|
||||
if reason == &FinishReason::Stop {
|
||||
log::info!("[DEBUG_LOG] send_message: Received finish_reason=stop after {} chunks", chunks_received);
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Received finish_reason=stop after {} chunks", chunks_received);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
log::error!("[DEBUG_LOG] send_message: Stream error after {} chunks: {:?}", chunks_received, e);
|
||||
log::error!("[DEBUG_LOG] send_message: Stream error details - model: '{}', chunks_received: {}", current_model, chunks_received);
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Stream error after {} chunks: {:?}", chunks_received, e);
|
||||
set_messages.update(|msgs| {
|
||||
msgs.push_back(Message {
|
||||
id: Uuid::new_v4().to_string(),
|
||||
role: "system".to_string(),
|
||||
content: format!("Stream error after {} chunks: {}", chunks_received, e),
|
||||
content: format!("Stream error: {}", e),
|
||||
timestamp: Date::now(),
|
||||
});
|
||||
});
|
||||
@@ -426,7 +349,6 @@ fn ChatInterface() -> impl IntoView {
|
||||
}
|
||||
}
|
||||
|
||||
// Cleanup: If we created an assistant message but no content ever arrived, remove the empty message
|
||||
if assistant_created && !content_appended {
|
||||
set_messages.update(|msgs| {
|
||||
let should_pop = msgs
|
||||
@@ -434,45 +356,19 @@ fn ChatInterface() -> impl IntoView {
|
||||
.map(|m| m.role == "assistant" && m.content.is_empty())
|
||||
.unwrap_or(false);
|
||||
if should_pop {
|
||||
log::info!("[DEBUG_LOG] send_message: Removing empty assistant message (no content received)");
|
||||
msgs.pop_back();
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
log::info!("[DEBUG_LOG] send_message: Stream completed successfully, received {} chunks", chunks_received);
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Stream completed successfully, received {} chunks", chunks_received);
|
||||
}
|
||||
Err(e) => {
|
||||
// Detailed error logging for different types of errors
|
||||
log::error!("[DEBUG_LOG] send_message: Request failed with error: {:?}", e);
|
||||
log::error!("[DEBUG_LOG] send_message: Request context - model: '{}', total_messages: {}, endpoint: http://localhost:8080/v1",
|
||||
current_model, total_messages);
|
||||
|
||||
// Try to extract more specific error information
|
||||
let error_details = format!("{:?}", e);
|
||||
let user_message = if error_details.contains("400") || error_details.contains("Bad Request") {
|
||||
log::error!("[DEBUG_LOG] send_message: HTTP 400 Bad Request detected - possible issues:");
|
||||
log::error!("[DEBUG_LOG] send_message: - Invalid model name: '{}'", current_model);
|
||||
log::error!("[DEBUG_LOG] send_message: - Invalid message format or content");
|
||||
log::error!("[DEBUG_LOG] send_message: - Server configuration issue");
|
||||
format!("Error: HTTP 400 Bad Request - Check model '{}' and message format. See console for details.", current_model)
|
||||
} else if error_details.contains("404") || error_details.contains("Not Found") {
|
||||
log::error!("[DEBUG_LOG] send_message: HTTP 404 Not Found - server endpoint may be incorrect");
|
||||
"Error: HTTP 404 Not Found - Server endpoint not found".to_string()
|
||||
} else if error_details.contains("500") || error_details.contains("Internal Server Error") {
|
||||
log::error!("[DEBUG_LOG] send_message: HTTP 500 Internal Server Error - server-side issue");
|
||||
"Error: HTTP 500 Internal Server Error - Server problem".to_string()
|
||||
} else if error_details.contains("Connection") || error_details.contains("connection") {
|
||||
log::error!("[DEBUG_LOG] send_message: Connection error - server may be down");
|
||||
"Error: Cannot connect to server at http://localhost:8080".to_string()
|
||||
} else {
|
||||
format!("Error: Request failed - {}", e)
|
||||
};
|
||||
|
||||
leptos::logging::log!("[DEBUG_LOG] send_message: Request failed with error: {:?}", e);
|
||||
let error_message = Message {
|
||||
id: Uuid::new_v4().to_string(),
|
||||
role: "system".to_string(),
|
||||
content: user_message,
|
||||
content: format!("Error: Request failed - {}", e),
|
||||
timestamp: Date::now(),
|
||||
};
|
||||
set_messages.update(|msgs| msgs.push_back(error_message));
|
||||
@@ -524,7 +420,7 @@ fn ChatInterface() -> impl IntoView {
|
||||
</div>
|
||||
}
|
||||
})
|
||||
.collect_view()
|
||||
.collect::<Vec<_>>()
|
||||
};
|
||||
|
||||
let loading_indicator = move || {
|
||||
@@ -551,21 +447,21 @@ fn ChatInterface() -> impl IntoView {
|
||||
>
|
||||
{move || {
|
||||
if models_loading.get() {
|
||||
view! {
|
||||
<option value="">"Loading models..."</option>
|
||||
}.into_view()
|
||||
vec![view! {
|
||||
<option value={String::from("")} selected=false>{String::from("Loading models...")}</option>
|
||||
}]
|
||||
} else {
|
||||
let models = available_models.get();
|
||||
if models.is_empty() {
|
||||
view! {
|
||||
<option selected=true value="gemma-3b-it">"gemma-3b-it (default)"</option>
|
||||
}.into_view()
|
||||
vec![view! {
|
||||
<option value={String::from("default")} selected=true>{String::from("default")}</option>
|
||||
}]
|
||||
} else {
|
||||
models.into_iter().map(|model| {
|
||||
view! {
|
||||
<option value=model.id.clone() selected={model.id == DEFAULT_MODEL}>{model.id}</option>
|
||||
<option value=model.id.clone() selected={model.id == DEFAULT_MODEL}>{model.id.clone()}</option>
|
||||
}
|
||||
}).collect_view()
|
||||
}).collect::<Vec<_>>()
|
||||
}
|
||||
}
|
||||
}}
|
||||
@@ -596,14 +492,3 @@ fn ChatInterface() -> impl IntoView {
|
||||
</div>
|
||||
}
|
||||
}
|
||||
|
||||
#[wasm_bindgen::prelude::wasm_bindgen(start)]
|
||||
pub fn main() {
|
||||
// Set up error handling and logging for WebAssembly
|
||||
console_error_panic_hook::set_once();
|
||||
console_log::init_with_level(log::Level::Debug).expect("error initializing logger");
|
||||
|
||||
// Mount the App component to the document body
|
||||
|
||||
leptos::mount_to_body(App)
|
||||
}
|
||||
30
crates/leptos-app/src/lib.rs
Normal file
30
crates/leptos-app/src/lib.rs
Normal file
@@ -0,0 +1,30 @@
|
||||
pub mod app;
|
||||
|
||||
#[cfg(feature = "hydrate")]
|
||||
#[wasm_bindgen::prelude::wasm_bindgen]
|
||||
pub fn hydrate() {
|
||||
use crate::app::*;
|
||||
console_error_panic_hook::set_once();
|
||||
leptos::mount::hydrate_body(App);
|
||||
}
|
||||
|
||||
#[cfg(feature = "ssr")]
|
||||
pub fn create_leptos_router() -> axum::Router {
|
||||
use axum::Router;
|
||||
use leptos::prelude::*;
|
||||
use leptos_axum::{generate_route_list, LeptosRoutes};
|
||||
use crate::app::*;
|
||||
|
||||
let conf = get_configuration(None).unwrap();
|
||||
let leptos_options = conf.leptos_options;
|
||||
// Generate the list of routes in your Leptos App
|
||||
let routes = generate_route_list(App);
|
||||
|
||||
Router::new()
|
||||
.leptos_routes(&leptos_options, routes, {
|
||||
let leptos_options = leptos_options.clone();
|
||||
move || shell(leptos_options.clone())
|
||||
})
|
||||
.fallback(leptos_axum::file_and_error_handler(shell))
|
||||
.with_state(leptos_options)
|
||||
}
|
||||
39
crates/leptos-app/src/main.rs
Normal file
39
crates/leptos-app/src/main.rs
Normal file
@@ -0,0 +1,39 @@
|
||||
|
||||
#[cfg(feature = "ssr")]
|
||||
#[tokio::main]
|
||||
async fn main() {
|
||||
use axum::Router;
|
||||
use leptos::logging::log;
|
||||
use leptos::prelude::*;
|
||||
use leptos_axum::{generate_route_list, LeptosRoutes};
|
||||
use leptos_app::app::*;
|
||||
|
||||
let conf = get_configuration(None).unwrap();
|
||||
let addr = conf.leptos_options.site_addr;
|
||||
let leptos_options = conf.leptos_options;
|
||||
// Generate the list of routes in your Leptos App
|
||||
let routes = generate_route_list(App);
|
||||
|
||||
let app = Router::new()
|
||||
.leptos_routes(&leptos_options, routes, {
|
||||
let leptos_options = leptos_options.clone();
|
||||
move || shell(leptos_options.clone())
|
||||
})
|
||||
.fallback(leptos_axum::file_and_error_handler(shell))
|
||||
.with_state(leptos_options);
|
||||
|
||||
// run our app with hyper
|
||||
// `axum::Server` is a re-export of `hyper::Server`
|
||||
log!("listening on http://{}", &addr);
|
||||
let listener = tokio::net::TcpListener::bind(&addr).await.unwrap();
|
||||
axum::serve(listener, app.into_make_service())
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "ssr"))]
|
||||
pub fn main() {
|
||||
// no client-side main function
|
||||
// unless we want this to work with e.g., Trunk for pure client-side testing
|
||||
// see lib.rs for hydration function instead
|
||||
}
|
||||
4
crates/leptos-app/style/main.scss
Normal file
4
crates/leptos-app/style/main.scss
Normal file
@@ -0,0 +1,4 @@
|
||||
body {
|
||||
font-family: sans-serif;
|
||||
text-align: center;
|
||||
}
|
||||
@@ -1,7 +0,0 @@
|
||||
*
|
||||
!src/
|
||||
!style/
|
||||
!Cargo.toml/
|
||||
!index.html
|
||||
!Trunk.toml
|
||||
|
||||
@@ -1,64 +0,0 @@
|
||||
[package]
|
||||
name = "leptos-chat"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
|
||||
[lib]
|
||||
crate-type = ["cdylib"]
|
||||
|
||||
[dependencies]
|
||||
leptos = { version = "0.6", features = ["csr"] }
|
||||
leptos_meta = { version = "0.6", features = ["csr"] }
|
||||
leptos_router = { version = "0.6", features = ["csr"] }
|
||||
wasm-bindgen = "0.2"
|
||||
console_error_panic_hook = "0.1"
|
||||
console_log = "1"
|
||||
log = "0.4"
|
||||
serde = { version = "1.0", features = ["derive"] }
|
||||
serde_json = "1.0"
|
||||
js-sys = "0.3"
|
||||
either = { version = "1.9", features = ["serde"] }
|
||||
# Make async-openai optional and only included for non-wasm targets
|
||||
async-openai-wasm = { default-features = false, version = "0.29" }
|
||||
# Only include tokio for non-wasm targets
|
||||
#tokio = { version = "1", default-features = false, features = ["sync", "macros", "io-util", "rt"] }
|
||||
#reqwest = {version = "0.12.23", default-features = false, optional = false}
|
||||
futures-util = "0.3"
|
||||
|
||||
|
||||
|
||||
web-sys = { version = "0.3", features = [
|
||||
"console",
|
||||
"Window",
|
||||
"Document",
|
||||
"Element",
|
||||
"HtmlElement",
|
||||
"HtmlInputElement",
|
||||
"HtmlSelectElement",
|
||||
"HtmlTextAreaElement",
|
||||
"Event",
|
||||
"EventTarget",
|
||||
"KeyboardEvent",
|
||||
] }
|
||||
gloo-net = "0.6.0"
|
||||
|
||||
[dependencies.uuid]
|
||||
version = "1.0"
|
||||
features = [
|
||||
"v4", # Lets you generate random UUIDs
|
||||
"fast-rng", # Use a faster (but still sufficiently random) RNG
|
||||
"macro-diagnostics", # Enable better diagnostics for compile-time UUIDs
|
||||
"js", # Enable JavaScript RNG for WASM targets
|
||||
]
|
||||
|
||||
# generates docker compose configuration
|
||||
[package.metadata.compose]
|
||||
image = "ghcr.io/geoffsee/leptos-chat:latest"
|
||||
port = 8788
|
||||
|
||||
|
||||
# generates kubernetes manifests
|
||||
[package.metadata.kube]
|
||||
image = "ghcr.io/geoffsee/leptos-chat:latest"
|
||||
replicas = 1
|
||||
port = 8788
|
||||
@@ -1,28 +0,0 @@
|
||||
# Build stage
|
||||
FROM rust:1-alpine AS builder
|
||||
|
||||
# Install build dependencies
|
||||
RUN apk add --no-cache npm nodejs musl-dev pkgconfig openssl-dev git curl bash
|
||||
|
||||
RUN curl -L --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/cargo-bins/cargo-binstall/main/install-from-binstall-release.sh | bash
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Copy manifest first (cache deps)
|
||||
COPY . .
|
||||
# Install trunk
|
||||
RUN cargo install wasm-bindgen-cli
|
||||
|
||||
RUN cargo binstall trunk
|
||||
|
||||
# Build release artifacts
|
||||
RUN rustup target add wasm32-unknown-unknown && export RUSTFLAGS='--cfg getrandom_backend="wasm_js"' && trunk build --release
|
||||
|
||||
# Final stage: static web server
|
||||
FROM caddy:2-alpine
|
||||
|
||||
# Copy built assets into Caddy's web root
|
||||
COPY --from=builder /app/dist /usr/share/caddy
|
||||
|
||||
EXPOSE 8788
|
||||
CMD ["caddy", "file-server", "--root", "/usr/share/caddy", "--listen", ":8788"]
|
||||
@@ -1,7 +0,0 @@
|
||||
[build]
|
||||
# Set the RUSTFLAGS environment variable for getrandom's WebAssembly support
|
||||
rustflags = ["--cfg", "getrandom_backend=\"wasm_js\""]
|
||||
|
||||
[serve]
|
||||
# Use the same port as in the run.sh script
|
||||
port = 8788
|
||||
@@ -1,15 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
<title>Chat Interface</title>
|
||||
<link rel="stylesheet" href="style/main.css" />
|
||||
</head>
|
||||
<body>
|
||||
<script type="module">
|
||||
import init from './pkg/leptos_chat.js';
|
||||
init();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1,6 +0,0 @@
|
||||
#!/usr/bin/env sh
|
||||
|
||||
# Set RUSTFLAGS for getrandom's WebAssembly support
|
||||
export RUSTFLAGS='--cfg getrandom_backend="wasm_js"'
|
||||
|
||||
trunk serve --port 8788
|
||||
@@ -1,165 +0,0 @@
|
||||
body {
|
||||
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
background-color: #f5f5f5;
|
||||
}
|
||||
|
||||
.chat-container {
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
height: 100vh;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
background-color: white;
|
||||
box-shadow: 0 0 20px rgba(0, 0, 0, 0.1);
|
||||
}
|
||||
|
||||
h1 {
|
||||
background-color: #4a90e2;
|
||||
color: white;
|
||||
margin: 0;
|
||||
padding: 20px;
|
||||
text-align: center;
|
||||
font-size: 24px;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.messages-container {
|
||||
flex: 1;
|
||||
overflow-y: auto;
|
||||
padding: 20px;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 15px;
|
||||
}
|
||||
|
||||
.message {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
max-width: 70%;
|
||||
padding: 12px 16px;
|
||||
border-radius: 18px;
|
||||
word-wrap: break-word;
|
||||
}
|
||||
|
||||
.user-message {
|
||||
align-self: flex-end;
|
||||
background-color: #4a90e2;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.assistant-message {
|
||||
align-self: flex-start;
|
||||
background-color: #e9ecef;
|
||||
color: #333;
|
||||
}
|
||||
|
||||
.system-message {
|
||||
align-self: center;
|
||||
background-color: #ffebcc;
|
||||
color: #856404;
|
||||
border: 1px solid #ffeaa7;
|
||||
}
|
||||
|
||||
.message-role {
|
||||
font-size: 12px;
|
||||
font-weight: 600;
|
||||
margin-bottom: 4px;
|
||||
opacity: 0.7;
|
||||
text-transform: capitalize;
|
||||
}
|
||||
|
||||
.message-content {
|
||||
font-size: 14px;
|
||||
line-height: 1.4;
|
||||
}
|
||||
|
||||
.input-form {
|
||||
display: flex;
|
||||
padding: 20px;
|
||||
gap: 10px;
|
||||
background-color: #f8f9fa;
|
||||
border-top: 1px solid #dee2e6;
|
||||
}
|
||||
|
||||
.message-input {
|
||||
flex: 1;
|
||||
padding: 12px 16px;
|
||||
border: 1px solid #ced4da;
|
||||
border-radius: 25px;
|
||||
font-size: 14px;
|
||||
outline: none;
|
||||
transition: border-color 0.2s ease;
|
||||
}
|
||||
|
||||
.message-input:focus {
|
||||
border-color: #4a90e2;
|
||||
box-shadow: 0 0 0 2px rgba(74, 144, 226, 0.25);
|
||||
}
|
||||
|
||||
.message-input:disabled {
|
||||
background-color: #f8f9fa;
|
||||
color: #6c757d;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.send-button {
|
||||
padding: 12px 24px;
|
||||
background-color: #4a90e2;
|
||||
color: white;
|
||||
border: none;
|
||||
border-radius: 25px;
|
||||
font-size: 14px;
|
||||
font-weight: 600;
|
||||
cursor: pointer;
|
||||
transition: background-color 0.2s ease;
|
||||
min-width: 80px;
|
||||
}
|
||||
|
||||
.send-button:hover:not(:disabled) {
|
||||
background-color: #357abd;
|
||||
}
|
||||
|
||||
.send-button:disabled {
|
||||
background-color: #6c757d;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
/* Scrollbar styling */
|
||||
.messages-container::-webkit-scrollbar {
|
||||
width: 8px;
|
||||
}
|
||||
|
||||
.messages-container::-webkit-scrollbar-track {
|
||||
background: #f1f1f1;
|
||||
}
|
||||
|
||||
.messages-container::-webkit-scrollbar-thumb {
|
||||
background: #c1c1c1;
|
||||
border-radius: 4px;
|
||||
}
|
||||
|
||||
.messages-container::-webkit-scrollbar-thumb:hover {
|
||||
background: #a1a1a1;
|
||||
}
|
||||
|
||||
/* Responsive design */
|
||||
@media (max-width: 768px) {
|
||||
.chat-container {
|
||||
height: 100vh;
|
||||
}
|
||||
|
||||
.message {
|
||||
max-width: 85%;
|
||||
}
|
||||
|
||||
.input-form {
|
||||
padding: 15px;
|
||||
}
|
||||
|
||||
h1 {
|
||||
padding: 15px;
|
||||
font-size: 20px;
|
||||
}
|
||||
}
|
||||
@@ -12,14 +12,14 @@ path = "src/main.rs"
|
||||
axum = "0.8.4"
|
||||
tokio = { version = "1.45.1", features = ["full"] }
|
||||
tower = "0.5.2"
|
||||
tower-http = { version = "0.6.6", features = ["trace", "cors"] }
|
||||
tower-http = { version = "0.6.6", features = ["trace", "cors", "fs"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = "1.0.140"
|
||||
tracing = "0.1"
|
||||
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
||||
uuid = { version = "1.7.0", features = ["v4"] }
|
||||
reqwest = { version = "0.12", features = ["json"] }
|
||||
rust-embed = "8.7.2"
|
||||
rust-embed = { version = "8.7.2", features = ["include-exclude"] }
|
||||
|
||||
# Dependencies for embeddings functionality
|
||||
embeddings-engine = { path = "../embeddings-engine" }
|
||||
@@ -27,6 +27,11 @@ embeddings-engine = { path = "../embeddings-engine" }
|
||||
# Dependencies for inference functionality
|
||||
inference-engine = { path = "../inference-engine" }
|
||||
|
||||
# Dependencies for leptos web app
|
||||
leptos-app = { path = "../leptos-app", features = ["ssr"] }
|
||||
|
||||
mime_guess = "2.0.5"
|
||||
|
||||
# generates docker compose configuration
|
||||
[package.metadata.compose]
|
||||
name = "predict-otron-9000"
|
||||
|
||||
@@ -89,7 +89,7 @@ impl ServerConfig {
|
||||
}
|
||||
}
|
||||
Err(_) => {
|
||||
tracing::info!("SERVER_CONFIG not set, using default Local mode");
|
||||
tracing::info!("SERVER_CONFIG not set, Standalone mode active");
|
||||
ServerConfig::default()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,22 +1,21 @@
|
||||
mod middleware;
|
||||
mod config;
|
||||
mod middleware;
|
||||
mod proxy;
|
||||
|
||||
use axum::{
|
||||
Router,
|
||||
serve,
|
||||
};
|
||||
use std::env;
|
||||
use axum::response::IntoResponse;
|
||||
use axum::routing::get;
|
||||
use tokio::net::TcpListener;
|
||||
use tower_http::trace::TraceLayer;
|
||||
use tower_http::cors::{Any, CorsLayer};
|
||||
use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};
|
||||
use inference_engine::AppState;
|
||||
use middleware::{MetricsStore, MetricsLoggerFuture, MetricsLayer};
|
||||
use axum::{Router, http::Uri, response::Html, serve};
|
||||
use config::ServerConfig;
|
||||
use inference_engine::AppState;
|
||||
use middleware::{MetricsLayer, MetricsLoggerFuture, MetricsStore};
|
||||
use proxy::create_proxy_router;
|
||||
|
||||
use rust_embed::Embed;
|
||||
use std::env;
|
||||
use tokio::net::TcpListener;
|
||||
use tower_http::classify::ServerErrorsFailureClass::StatusCode;
|
||||
use tower_http::cors::{Any, CorsLayer};
|
||||
use tower_http::trace::TraceLayer;
|
||||
use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};
|
||||
|
||||
#[tokio::main]
|
||||
async fn main() {
|
||||
@@ -34,7 +33,6 @@ async fn main() {
|
||||
.with(tracing_subscriber::fmt::layer())
|
||||
.init();
|
||||
|
||||
|
||||
// Initialize metrics store for performance tracking
|
||||
let metrics_store = MetricsStore::new();
|
||||
|
||||
@@ -55,19 +53,22 @@ async fn main() {
|
||||
let service_router = if server_config.clone().is_high_availability() {
|
||||
tracing::info!("Running in HighAvailability mode - proxying to external services");
|
||||
tracing::info!(" Inference service URL: {}", server_config.inference_url());
|
||||
tracing::info!(" Embeddings service URL: {}", server_config.embeddings_url());
|
||||
tracing::info!(
|
||||
" Embeddings service URL: {}",
|
||||
server_config.embeddings_url()
|
||||
);
|
||||
|
||||
// Use proxy router that forwards requests to external services
|
||||
create_proxy_router(server_config.clone())
|
||||
} else {
|
||||
tracing::info!("Running in Local mode - using embedded services");
|
||||
tracing::info!("Running in Standalone mode - using embedded services");
|
||||
|
||||
// Create unified router by merging embeddings and inference routers (existing behavior)
|
||||
let embeddings_router = embeddings_engine::create_embeddings_router();
|
||||
|
||||
// Create AppState with correct model configuration
|
||||
use inference_engine::server::{PipelineArgs, build_pipeline};
|
||||
use inference_engine::Which;
|
||||
use inference_engine::server::{PipelineArgs, build_pipeline};
|
||||
let mut pipeline_args = PipelineArgs::default();
|
||||
pipeline_args.model_id = "google/gemma-3-1b-it".to_string();
|
||||
pipeline_args.which = Which::InstructV3_1B;
|
||||
@@ -98,39 +99,41 @@ async fn main() {
|
||||
// Create metrics layer
|
||||
let metrics_layer = MetricsLayer::new(metrics_store);
|
||||
|
||||
// Create the leptos router for the web frontend
|
||||
let leptos_router = leptos_app::create_leptos_router();
|
||||
|
||||
// Merge the service router with base routes and add middleware layers
|
||||
let app = Router::new()
|
||||
.route("/", get(|| async { "API ready. This can serve the Leptos web app, but it doesn't." }))
|
||||
.route("/health", get(|| async { "ok" }))
|
||||
.merge(service_router)
|
||||
.layer(metrics_layer) // Add metrics tracking
|
||||
.merge(leptos_router) // Add leptos web frontend routes
|
||||
.layer(metrics_layer) // Add metrics tracking
|
||||
.layer(cors)
|
||||
.layer(TraceLayer::new_for_http());
|
||||
|
||||
// Server configuration
|
||||
let server_host = env::var("SERVER_HOST").unwrap_or_else(|_| {
|
||||
String::from(default_host)
|
||||
});
|
||||
let server_host = env::var("SERVER_HOST").unwrap_or_else(|_| String::from(default_host));
|
||||
|
||||
let server_port = env::var("SERVER_PORT").map(|v| v.parse::<u16>().unwrap_or(default_port)).unwrap_or_else(|_| {
|
||||
default_port
|
||||
});
|
||||
let server_port = env::var("SERVER_PORT")
|
||||
.map(|v| v.parse::<u16>().unwrap_or(default_port))
|
||||
.unwrap_or_else(|_| default_port);
|
||||
|
||||
let server_address = format!("{}:{}", server_host, server_port);
|
||||
|
||||
|
||||
let listener = TcpListener::bind(&server_address).await.unwrap();
|
||||
tracing::info!("Unified predict-otron-9000 server listening on {}", listener.local_addr().unwrap());
|
||||
tracing::info!(
|
||||
"Unified predict-otron-9000 server listening on {}",
|
||||
listener.local_addr().unwrap()
|
||||
);
|
||||
tracing::info!("Performance metrics tracking enabled - summary logs every 60 seconds");
|
||||
tracing::info!("Available endpoints:");
|
||||
tracing::info!(" GET / - Root endpoint from embeddings-engine");
|
||||
tracing::info!(" POST /v1/embeddings - Text embeddings");
|
||||
tracing::info!(" POST /v1/chat/completions - Chat completions");
|
||||
tracing::info!(" GET / - Leptos chat web application");
|
||||
tracing::info!(" GET /health - Health check");
|
||||
tracing::info!(" POST /v1/embeddings - Text embeddings API");
|
||||
tracing::info!(" POST /v1/chat/completions - Chat completions API");
|
||||
|
||||
serve(listener, app).await.unwrap();
|
||||
}
|
||||
|
||||
|
||||
|
||||
// Chat completions handler that properly uses the inference server crate's error handling
|
||||
// This function is no longer needed as we're using the inference_engine router directly
|
||||
|
||||
@@ -25,22 +25,6 @@ services:
|
||||
retries: 10
|
||||
start_period: 10s
|
||||
|
||||
# Web frontend - Leptos WASM chat interface
|
||||
leptos-chat:
|
||||
build:
|
||||
context: crates/leptos-chat
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "8788:8788"
|
||||
depends_on:
|
||||
predict-otron-9000:
|
||||
condition: service_healthy
|
||||
networks:
|
||||
- predict-otron-network
|
||||
environment:
|
||||
# Configure API endpoint for the frontend to connect to backend
|
||||
- API_BASE_URL=http://predict-otron-9000:8080
|
||||
|
||||
volumes:
|
||||
# Persistent storage for Hugging Face model cache
|
||||
hf-cache:
|
||||
|
||||
@@ -173,7 +173,7 @@ The server logs the selected mode on startup:
|
||||
|
||||
**Local Mode:**
|
||||
```
|
||||
INFO predict_otron_9000: Running in Local mode - using embedded services
|
||||
INFO predict_otron_9000: Running in Standalone mode
|
||||
```
|
||||
|
||||
**HighAvailability Mode:**
|
||||
|
||||
33
package-lock.json
generated
33
package-lock.json
generated
@@ -1,33 +0,0 @@
|
||||
{
|
||||
"name": "predict-otron-9000",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"dependencies": {
|
||||
"openai": "^5.16.0"
|
||||
}
|
||||
},
|
||||
"node_modules/openai": {
|
||||
"version": "5.16.0",
|
||||
"resolved": "https://registry.npmjs.org/openai/-/openai-5.16.0.tgz",
|
||||
"integrity": "sha512-hoEH8ZNvg1HXjU9mp88L/ZH8O082Z8r6FHCXGiWAzVRrEv443aI57qhch4snu07yQydj+AUAWLenAiBXhu89Tw==",
|
||||
"license": "Apache-2.0",
|
||||
"bin": {
|
||||
"openai": "bin/cli"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"ws": "^8.18.0",
|
||||
"zod": "^3.23.8"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"ws": {
|
||||
"optional": true
|
||||
},
|
||||
"zod": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -59,11 +59,11 @@ echo "[INFO] Server is ready!"
|
||||
|
||||
# Run first CLI request
|
||||
echo "[INFO] Running first CLI request - listing models..."
|
||||
bun run cli.ts --list-models
|
||||
./cli.ts --list-models
|
||||
|
||||
echo ""
|
||||
echo "[INFO] Running second CLI request - chat completion..."
|
||||
bun run cli.ts "What is 2+2?"
|
||||
./cli.ts "What is 2+2?"
|
||||
|
||||
echo ""
|
||||
echo "[INFO] Both CLI requests completed successfully!"
|
||||
Reference in New Issue
Block a user