From 9f9b48ec06dc9242f6cd5822742f41c180435f3d Mon Sep 17 00:00:00 2001
From: Andrew Lapp <andrew@github.rew.la>
Date: Sat, 27 Jul 2024 11:16:22 -0500
Subject: [PATCH] Add experimental-warning to CFGGuide, update warning-linked
 docs

---
 docs/reference/cfg.md | 9 +++++++--
 outlines/fsm/guide.py | 6 ++++++
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/docs/reference/cfg.md b/docs/reference/cfg.md
index 4f0285c11..e3b177800 100644
--- a/docs/reference/cfg.md
+++ b/docs/reference/cfg.md
@@ -30,10 +30,15 @@ print(sequence)
 # (8-2)
 ```
 
-!!! Note "Performance"
+###### Disclaimer
 
-    The implementation of grammar-structured generation in Outlines is very naive. This does not reflect the performance of [.txt](https://dottxt.co)'s product, where we made grammar-structured generation as fast as regex-structured generation.
+!!! Note "Experimental"
 
+    Outlines current **community-contributed** implementation of CFG-structured generation is experimental. This does not reflect the performance of [.txt](https://dottxt.co)'s product, where we have optimized grammar-structured generation to be as fast as regex-structured generation. Additionally, it does not fully align with the approach described in our [technical report](https://arxiv.org/pdf/2307.09702), aside from its use of incremental/partial parsing. This feature is still a work in progress, requiring performance enhancements and bug fixes for an ideal implementation. For more details, please see our [grammar-related open issues on GitHub](https://github.com/outlines-dev/outlines/issues?q=is%3Aissue+is%3Aopen+label%3Agrammar).
+
+!!! Note "Greedy"
+
+    To mitigate performance issues, CFG-structured generation will use rejection sampling and iterate over the candidate tokens highest logit first,, completing once a single valid token ID is selected. This is effectively greedy generation.
 
 ## Ready-to-use grammars
 
diff --git a/outlines/fsm/guide.py b/outlines/fsm/guide.py
index aa073d107..44a918494 100644
--- a/outlines/fsm/guide.py
+++ b/outlines/fsm/guide.py
@@ -1,5 +1,6 @@
 import collections
 import copy
+import warnings
 from dataclasses import dataclass
 from typing import (
     TYPE_CHECKING,
@@ -319,6 +320,11 @@ def __init__(self, cfg_string: str, tokenizer):
         """
         Construct the PartialLark parser and set the empty initial_state (PartialParserState)
         """
+        warnings.warn(
+            "Outlines' public *community-contributed* CFG structured generation is experimental. "
+            "Please review https://outlines-dev.github.io/outlines/reference/cfg#disclaimer"
+        )
+
         self.cfg_string = cfg_string
         self.tokenizer = tokenizer
         self.eos_token_id = self.tokenizer.eos_token_id