liter_llm 1.0.0.pre.rc.6

data/vendor/liter-llm/README.md

@@ -0,0 +1,252 @@
+# Rust
+
+<div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
+  <!-- Language Bindings -->
+  <a href="https://crates.io/crates/liter-llm">
+    <img src="https://img.shields.io/crates/v/liter-llm?label=Rust&color=007ec6" alt="Rust">
+  </a>
+  <a href="https://pypi.org/project/liter-llm/">
+    <img src="https://img.shields.io/pypi/v/liter-llm?label=Python&color=007ec6" alt="Python">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/liter-llm">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/liter-llm?label=Node.js&color=007ec6" alt="Node.js">
+  </a>
+  <a href="https://www.npmjs.com/package/@kreuzberg/liter-llm-wasm">
+    <img src="https://img.shields.io/npm/v/@kreuzberg/liter-llm-wasm?label=WASM&color=007ec6" alt="WASM">
+  </a>
+  <a href="https://central.sonatype.com/artifact/dev.kreuzberg/liter-llm">
+    <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/liter-llm?label=Java&color=007ec6" alt="Java">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/liter-llm/tree/main/packages/go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/liter-llm?label=Go&color=007ec6" alt="Go">
+  </a>
+  <a href="https://www.nuget.org/packages/LiterLlm">
+    <img src="https://img.shields.io/nuget/v/LiterLlm?label=C%23&color=007ec6" alt="C#">
+  </a>
+  <a href="https://packagist.org/packages/kreuzberg/liter-llm">
+    <img src="https://img.shields.io/packagist/v/kreuzberg/liter-llm?label=PHP&color=007ec6" alt="PHP">
+  </a>
+  <a href="https://rubygems.org/gems/liter_llm">
+    <img src="https://img.shields.io/gem/v/liter_llm?label=Ruby&color=007ec6" alt="Ruby">
+  </a>
+  <a href="https://hex.pm/packages/liter_llm">
+    <img src="https://img.shields.io/hexpm/v/liter_llm?label=Elixir&color=007ec6" alt="Elixir">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/liter-llm/pkgs/container/liter-llm">
+    <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
+  </a>
+  <a href="https://github.com/kreuzberg-dev/liter-llm/tree/main/crates/liter-llm-ffi">
+    <img src="https://img.shields.io/badge/C-FFI-007ec6" alt="C FFI">
+  </a>
+
+  <!-- Project Info -->
+  <a href="https://github.com/kreuzberg-dev/liter-llm/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License">
+  </a>
+  <a href="https://docs.liter-llm.kreuzberg.dev">
+    <img src="https://img.shields.io/badge/docs-kreuzberg.dev-007ec6" alt="Docs">
+  </a>
+</div>
+
+
+<div align="center" style="margin: 20px 0;">
+  <picture>
+    <img width="100%" alt="kreuzberg.dev" src="https://github.com/user-attachments/assets/1b6c6ad7-3b6d-4171-b1c9-f2026cc9deb8" />
+  </picture>
+</div>
+
+
+<div align="center" style="margin-bottom: 20px;">
+  <a href="https://discord.gg/xt9WY3GnKR">
+    <img height="22" src="https://img.shields.io/badge/Discord-Join%20our%20community-7289da?logo=discord&logoColor=white" alt="Discord">
+  </a>
+</div>
+
+
+Universal LLM API client for Rust. Access 142+ LLM providers — OpenAI, Anthropic, Groq, Mistral, and more — through a single unified interface. Async/await with Tokio, streaming via BoxStream, composable Tower middleware stack, and compile-time type safety.
+
+
+## Installation
+
+### Package Installation
+
+
+
+
+
+
+### System Requirements
+
+
+- See [Installation Guide](https://github.com/kreuzberg-dev/liter-llm#installation) for requirements
+
+
+
+## Quick Start
+
+### Basic Chat
+
+Send a message to any provider using the `provider/model` prefix:
+
+```rust
+use liter_llm::{
+    ChatCompletionRequest, ClientConfigBuilder, DefaultClient, LlmClient,
+    Message, UserContent, UserMessage,
+};
+
+#[tokio::main]
+async fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let config = ClientConfigBuilder::new(std::env::var("OPENAI_API_KEY")?)
+        .build();
+    let client = DefaultClient::new(config, Some("openai/gpt-4o"))?;
+
+    let request = ChatCompletionRequest {
+        model: "openai/gpt-4o".into(),
+        messages: vec![Message::User(UserMessage {
+            content: UserContent::Text("Hello!".into()),
+            name: None,
+        })],
+        ..Default::default()
+    };
+
+    let response = client.chat(request).await?;
+    if let Some(choice) = response.choices.first() {
+        println!("{}", choice.message.content.as_deref().unwrap_or(""));
+    }
+    Ok(())
+}
+```
+
+
+### Common Use Cases
+
+
+#### Streaming Responses
+
+Stream tokens in real time:
+
+```rust
+use futures::StreamExt;
+use liter_llm::{
+    ChatCompletionRequest, ClientConfigBuilder, DefaultClient, LlmClient,
+    Message, UserContent, UserMessage,
+};
+
+#[tokio::main]
+async fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let config = ClientConfigBuilder::new(std::env::var("OPENAI_API_KEY")?)
+        .build();
+    let client = DefaultClient::new(config, Some("openai/gpt-4o"))?;
+
+    let request = ChatCompletionRequest {
+        model: "openai/gpt-4o".into(),
+        messages: vec![Message::User(UserMessage {
+            content: UserContent::Text("Tell me a story".into()),
+            name: None,
+        })],
+        ..Default::default()
+    };
+
+    let mut stream = client.chat_stream(request).await?;
+    while let Some(chunk) = stream.next().await {
+        let chunk = chunk?;
+        if let Some(choice) = chunk.choices.first() {
+            if let Some(content) = &choice.delta.content {
+                print!("{content}");
+            }
+        }
+    }
+    println!();
+    Ok(())
+}
+```
+
+
+
+
+
+### Next Steps
+
+- **[Provider Registry](https://github.com/kreuzberg-dev/liter-llm/blob/main/schemas/providers.json)** - Full list of supported providers
+- **[GitHub Repository](https://github.com/kreuzberg-dev/liter-llm)** - Source, issues, and discussions
+
+
+
+## Features
+
+### Supported Providers (142+)
+
+Route to any provider using the `provider/model` prefix convention:
+
+| Provider | Example Model |
+|----------|--------------|
+| **OpenAI** | `openai/gpt-4o`, `openai/gpt-4o-mini` |
+| **Anthropic** | `anthropic/claude-3-5-sonnet-20241022` |
+| **Groq** | `groq/llama-3.1-70b-versatile` |
+| **Mistral** | `mistral/mistral-large-latest` |
+| **Cohere** | `cohere/command-r-plus` |
+| **Together AI** | `together/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` |
+| **Fireworks** | `fireworks/accounts/fireworks/models/llama-v3p1-70b-instruct` |
+| **Google Vertex** | `vertexai/gemini-1.5-pro` |
+| **Amazon Bedrock** | `bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0` |
+
+**[Complete Provider List](https://github.com/kreuzberg-dev/liter-llm/blob/main/schemas/providers.json)**
+
+### Key Capabilities
+
+- **Provider Routing** -- Single client for 142+ LLM providers via `provider/model` prefix
+- **Unified API** -- Consistent `chat`, `chat_stream`, `embeddings`, `list_models` interface
+
+- **Streaming** -- Real-time token streaming via `chat_stream`
+
+
+- **Tool Calling** -- Function calling and tool use across all supporting providers
+
+- **Type Safe** -- Schema-driven types compiled from JSON schemas
+- **Secure** -- API keys never logged or serialized, managed via environment variables
+- **Observability** -- Built-in [OpenTelemetry](https://opentelemetry.io/docs/specs/semconv/gen-ai/) with GenAI semantic conventions
+- **Error Handling** -- Structured errors with provider context and retry hints
+
+### Performance
+
+Built on a compiled Rust core for speed and safety:
+
+- **Provider resolution** at client construction -- zero per-request overhead
+- **Configurable timeouts** and connection pooling
+- **Zero-copy streaming** with SSE and AWS EventStream support
+- **API keys** wrapped in secure memory, zeroed on drop
+
+
+
+## Provider Routing
+
+Route to 142+ providers using the `provider/model` prefix convention:
+
+```text
+openai/gpt-4o
+anthropic/claude-3-5-sonnet-20241022
+groq/llama-3.1-70b-versatile
+mistral/mistral-large-latest
+```
+
+See the [provider registry](https://github.com/kreuzberg-dev/liter-llm/blob/main/schemas/providers.json) for the full list.
+
+
+
+## Documentation
+
+- **[Documentation](https://docs.liter-llm.kreuzberg.dev)** -- Full docs and API reference
+- **[GitHub Repository](https://github.com/kreuzberg-dev/liter-llm)** -- Source, issues, and discussions
+- **[Provider Registry](https://github.com/kreuzberg-dev/liter-llm/blob/main/schemas/providers.json)** -- 142 supported providers
+
+Part of [kreuzberg.dev](https://kreuzberg.dev).
+
+## Contributing
+
+Contributions are welcome! See [CONTRIBUTING.md](https://github.com/kreuzberg-dev/liter-llm/blob/main/CONTRIBUTING.md) for guidelines.
+
+Join our [Discord community](https://discord.gg/xt9WY3GnKR) for questions and discussion.
+
+## License
+
+MIT -- see [LICENSE](https://github.com/kreuzberg-dev/liter-llm/blob/main/LICENSE) for details.

data/vendor/liter-llm/schemas/pricing.json

@@ -0,0 +1,40 @@
+{
+	"$comment": "Model pricing data derived from litellm (MIT License, Copyright 2023 Berri AI). Prices in USD per token. Source: https://github.com/BerriAI/litellm",
+	"models": {
+		"gpt-4": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 },
+		"gpt-4-turbo": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 },
+		"gpt-4o": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 },
+		"gpt-4o-mini": { "input_cost_per_token": 0.00000015, "output_cost_per_token": 0.0000006 },
+		"gpt-3.5-turbo": { "input_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000015 },
+		"o1": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 },
+		"o3": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 },
+		"o3-mini": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 },
+		"claude-3-haiku-20240307": { "input_cost_per_token": 0.00000025, "output_cost_per_token": 0.00000125 },
+		"claude-3-opus-20240229": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 },
+		"claude-3-7-sonnet-20250219": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-haiku-4-5": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 },
+		"claude-haiku-4-5-20251001": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 },
+		"claude-sonnet-4-5": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-sonnet-4-5-20250929": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-sonnet-4-6": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-4-sonnet-20250514": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-sonnet-4-20250514": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 },
+		"claude-opus-4-1": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 },
+		"claude-opus-4-5": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 },
+		"claude-opus-4-6": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 },
+		"claude-4-opus-20250514": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 },
+		"gemini-2.0-flash": { "input_cost_per_token": 0.0000001, "output_cost_per_token": 0.0000004 },
+		"gemini-2.0-flash-lite": { "input_cost_per_token": 0.000000075, "output_cost_per_token": 0.0000003 },
+		"gemini-2.5-flash": { "input_cost_per_token": 0.0000003, "output_cost_per_token": 0.0000025 },
+		"gemini-2.5-pro": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 },
+		"text-embedding-3-small": { "input_cost_per_token": 0.00000002, "output_cost_per_token": 0.0 },
+		"text-embedding-3-large": { "input_cost_per_token": 0.00000013, "output_cost_per_token": 0.0 },
+		"text-embedding-ada-002": { "input_cost_per_token": 0.0000001, "output_cost_per_token": 0.0 },
+		"deepseek/deepseek-chat": { "input_cost_per_token": 0.00000028, "output_cost_per_token": 0.00000042 },
+		"deepseek/deepseek-r1": { "input_cost_per_token": 0.00000055, "output_cost_per_token": 0.00000219 },
+		"mistral/mistral-large-latest": { "input_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000015 },
+		"mistral/mistral-small-latest": { "input_cost_per_token": 0.00000006, "output_cost_per_token": 0.00000018 },
+		"groq/llama-3.1-8b-instant": { "input_cost_per_token": 0.00000005, "output_cost_per_token": 0.00000008 },
+		"groq/llama-3.3-70b-versatile": { "input_cost_per_token": 0.00000059, "output_cost_per_token": 0.00000079 }
+	}
+}