Clean up ChainOfThoughtWithHint in DSPy 3.0 (#8395)

* fix

* add doc string

* clean up ChainOfThoughtWithHint

* done

* Clean up usage leftovers

* minor

---------

Co-authored-by: chenmoneygithub <chen.qian@databricks.com>

Author: Hangzhi

docs/docs/api/modules/ChainOfThoughtWithHint.md

@@ -145,17 +145,6 @@ question='What is the color of the sky?'
 pred = generate_answer(question=question)
 ```
 
-### dspy.ChainOfThoughtwithHint
-
-```python
-generate_answer = dspy.ChainOfThoughtWithHint(BasicQA)
-
-# Call the predictor on a particular input alongside a hint.
-question='What is the color of the sky?'
-hint = "It's what you often see during a sunny day."
-pred = generate_answer(question=question, hint=hint)
-```
-
 ### dspy.ProgramOfThought
 
 ```python

docs/docs/cheatsheet.md

@@ -358,23 +358,20 @@ Given a few tens or hundreds of representative _inputs_ of your task and a _metr
         For a complete RAG example that you can run, start this [tutorial](/tutorials/rag/). It improves the quality of a RAG system over a subset of StackExchange communities by 10% relative gain.
 
     === "Optimizing weights for Classification"
-        This is a minimal but fully runnable example of setting up a `dspy.ChainOfThought` module that classifies
-        short texts into one of 77 banking labels and then using `dspy.BootstrapFinetune` with 2000 text-label pairs
-        from the `Banking77` to finetune the weights of GPT-4o-mini for this task. We use the variant
-        `dspy.ChainOfThoughtWithHint`, which takes an optional `hint` at bootstrapping time, to maximize the utility of
-        the training data. Naturally, hints are not available at test time.
-
         <details><summary>Click to show dataset setup code.</summary>
 
         ```python linenums="1"
         import random
         from typing import Literal
-        from dspy.datasets import DataLoader
+
         from datasets import load_dataset
 
+        import dspy
+        from dspy.datasets import DataLoader
+
         # Load the Banking77 dataset.
-        CLASSES = load_dataset("PolyAI/banking77", split="train", trust_remote_code=True).features['label'].names
-        kwargs = dict(fields=("text", "label"), input_keys=("text",), split="train", trust_remote_code=True)
+        CLASSES = load_dataset("PolyAI/banking77", split="train", trust_remote_code=True).features["label"].names
+        kwargs = {"fields": ("text", "label"), "input_keys": ("text",), "split": "train", "trust_remote_code": True}
 
         # Load the first 2000 examples from the dataset, and assign a hint to each *training* example.
         trainset = [
@@ -388,10 +385,10 @@ Given a few tens or hundreds of representative _inputs_ of your task and a _metr
         ```python linenums="1"
         import dspy
         dspy.configure(lm=dspy.LM('openai/gpt-4o-mini-2024-07-18'))
-        
+
         # Define the DSPy module for classification. It will use the hint at training time, if available.
-        signature = dspy.Signature("text -> label").with_updated_fields('label', type_=Literal[tuple(CLASSES)])
-        classify = dspy.ChainOfThoughtWithHint(signature)
+        signature = dspy.Signature("text, hint -> label").with_updated_fields('label', type_=Literal[tuple(CLASSES)])
+        classify = dspy.ChainOfThought(signature)
 
         # Optimize via BootstrapFinetune.
         optimizer = dspy.BootstrapFinetune(metric=(lambda x, y, trace=None: x.label == y.label), num_threads=24)

docs/docs/index.md

@@ -150,23 +150,20 @@ optimized_program = teleprompter.compile(YOUR_PROGRAM_HERE, trainset=YOUR_TRAINS
         For a complete RAG example that you can run, start this [tutorial](/tutorials/rag/). It improves the quality of a RAG system over a subset of StackExchange communities from 53% to 61%.
 
     === "Optimizing weights for Classification"
-        This is a minimal but fully runnable example of setting up a `dspy.ChainOfThought` module that classifies
-        short texts into one of 77 banking labels and then using `dspy.BootstrapFinetune` with 2000 text-label pairs
-        from the `Banking77` to finetune the weights of GPT-4o-mini for this task. We use the variant
-        `dspy.ChainOfThoughtWithHint`, which takes an optional `hint` at bootstrapping time, to maximize the utility of
-        the training data. Naturally, hints are not available at test time. More can be found in this [tutorial](/tutorials/classification_finetuning/).
-
         <details><summary>Click to show dataset setup code.</summary>
 
         ```python linenums="1"
         import random
         from typing import Literal
-        from dspy.datasets import DataLoader
+
         from datasets import load_dataset
 
+        import dspy
+        from dspy.datasets import DataLoader
+
         # Load the Banking77 dataset.
-        CLASSES = load_dataset("PolyAI/banking77", split="train", trust_remote_code=True).features['label'].names
-        kwargs = dict(fields=("text", "label"), input_keys=("text",), split="train", trust_remote_code=True)
+        CLASSES = load_dataset("PolyAI/banking77", split="train", trust_remote_code=True).features["label"].names
+        kwargs = {"fields": ("text", "label"), "input_keys": ("text",), "split": "train", "trust_remote_code": True}
 
         # Load the first 2000 examples from the dataset, and assign a hint to each *training* example.
         trainset = [
@@ -179,11 +176,11 @@ optimized_program = teleprompter.compile(YOUR_PROGRAM_HERE, trainset=YOUR_TRAINS
 
         ```python linenums="1"
         import dspy
-        dspy.configure(lm=dspy.LM('gpt-4o-mini-2024-07-18'))
-        
+        dspy.configure(lm=dspy.LM('openai/gpt-4o-mini-2024-07-18'))
+
         # Define the DSPy module for classification. It will use the hint at training time, if available.
-        signature = dspy.Signature("text -> label").with_updated_fields('label', type_=Literal[tuple(CLASSES)])
-        classify = dspy.ChainOfThoughtWithHint(signature)
+        signature = dspy.Signature("text, hint -> label").with_updated_fields('label', type_=Literal[tuple(CLASSES)])
+        classify = dspy.ChainOfThought(signature)
 
         # Optimize via BootstrapFinetune.
         optimizer = dspy.BootstrapFinetune(metric=(lambda x, y, trace=None: x.label == y.label), num_threads=24)

docs/docs/learn/optimization/optimizers.md

@@ -88,7 +88,6 @@ nav:
         - Modules:
             - BestOfN: api/modules/BestOfN.md
             - ChainOfThought: api/modules/ChainOfThought.md
-            - ChainOfThoughtWithHint: api/modules/ChainOfThoughtWithHint.md
             - CodeAct: api/modules/CodeAct.md
             - Module: api/modules/Module.md
             - MultiChainComparison: api/modules/MultiChainComparison.md

docs/mkdocs.yml

@@ -36,7 +36,6 @@
         dspy.ReAct,
         dspy.ProgramOfThought,
         dspy.MultiChainComparison,
-        dspy.ChainOfThoughtWithHint,
         dspy.Parallel,
         dspy.BestOfN,
         dspy.Refine,

docs/scripts/generate_api_docs.py

@@ -1,7 +1,6 @@
 from dspy.predict.aggregation import majority
 from dspy.predict.best_of_n import BestOfN
 from dspy.predict.chain_of_thought import ChainOfThought
-from dspy.predict.chain_of_thought_with_hint import ChainOfThoughtWithHint
 from dspy.predict.code_act import CodeAct
 from dspy.predict.knn import KNN
 from dspy.predict.multi_chain_comparison import MultiChainComparison
@@ -15,7 +14,6 @@
     "majority",
     "BestOfN",
     "ChainOfThought",
-    "ChainOfThoughtWithHint",
     "CodeAct",
     "KNN",
     "MultiChainComparison",