1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
// SPDX-FileCopyrightText: Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//! Prompt Formatting Module
//!
//! Handles formatting of LLM request prompts, including:
//! - Chat template rendering
//! - Tool usage formatting
//! - Generation prompt handling
//!
//! The module supports different prompt formatting strategies through the
//! PromptFormatter
// TODO:
// 1. Query if `add_generation_prompt` is present in the prompt template
// 2. Support for models with add_generation_prompt:
// - PALS (Prefix-Assisted Language Sampling)
// - Continuation - Detected on user turns, where we can return
// partial assistant responses without add_generation_prompt
use Result;
use Value;
use Arc;
pub use ContextMixins;
/// Trait that defines a request that can map to an OpenAI-like request.