wip prompt refactor

langchain/chains/self_ask_with_search/examples.json

@@ -0,0 +1,18 @@
+[
+  {
+    "question": "Who lived longer, Muhammad Ali or Alan Turing?",
+    "answer": "Are follow up questions needed here: Yes.\nFollow up: How old was Muhammad Ali when he died?\nIntermediate answer: Muhammad Ali was 74 years old when he died.\nFollow up: How old was Alan Turing when he died?\nIntermediate answer: Alan Turing was 41 years old when he died.\nSo the final answer is: Muhammad Ali"
+  },
+  {
+    "question": "When was the founder of craigslist born?",
+    "answer": "Are follow up questions needed here: Yes.\nFollow up: Who was the founder of craigslist?\nIntermediate answer: Craigslist was founded by Craig Newmark.\nFollow up: When was Craig Newmark born?\nIntermediate answer: Craig Newmark was born on December 6, 1952.\nSo the final answer is: December 6, 1952"
+  },
+  {
+    "question": "Who was the maternal grandfather of George Washington?",
+    "answer": "Are follow up questions needed here: Yes.\nFollow up: Who was the mother of George Washington?\nIntermediate answer: The mother of George Washington was Mary Ball Washington.\nFollow up: Who was the father of Mary Ball Washington?\nIntermediate answer: The father of Mary Ball Washington was Joseph Ball.\nSo the final answer is: Joseph Ball"
+  },
+  {
+    "question": "Are both the directors of Jaws and Casino Royale from the same country?",
+    "answer": "Are follow up questions needed here: Yes.\nFollow up: Who is the director of Jaws?\nIntermediate Answer: The director of Jaws is Steven Spielberg.\nFollow up: Where is Steven Spielberg from?\nIntermediate Answer: The United States.\nFollow up: Who is the director of Casino Royale?\nIntermediate Answer: The director of Casino Royale is Martin Campbell.\nFollow up: Where is Martin Campbell from?\nIntermediate Answer: New Zealand.\nSo the final answer is: No"
+  }
+]

langchain/chains/self_ask_with_search/prompt.py

@@ -1,13 +1,25 @@
 # flake8: noqa
-from langchain.prompts.prompt import Prompt
+from langchain.prompts.dynamic import
+from langchain.prompts.data import BaseExample
+from pathlib import Path
+
+example_path = Path(__file__).parent / "examples.json"
+import json
+
+
+class SelfAskWithSearchExample(BaseExample):
+    question: str
+    answer: str
+
+    def formatted(self) -> str:
+        return f"Question: {self.question}\n{self.answer}"
+
+with open(example_path) as f:
+    raw_examples = json.load(f)
+    examples = [SelfAskWithSearchExample(**example) for example in raw_examples]
 
 _DEFAULT_TEMPLATE = """Question: Who lived longer, Muhammad Ali or Alan Turing?
-Are follow up questions needed here: Yes.
-Follow up: How old was Muhammad Ali when he died?
-Intermediate answer: Muhammad Ali was 74 years old when he died.
-Follow up: How old was Alan Turing when he died?
-Intermediate answer: Alan Turing was 41 years old when he died.
-So the final answer is: Muhammad Ali
+
 
 Question: When was the founder of craigslist born?
 Are follow up questions needed here: Yes.

langchain/prompts/data.py

@@ -0,0 +1,18 @@
+from pydantic import BaseModel
+from abc import abstractmethod, ABC
+
+class BaseExample(BaseModel, ABC):
+    """Base class for examples."""
+
+    @abstractmethod
+    @property
+    def formatted(self) -> str:
+        """Returns a formatted example as a string."""
+
+
+class SimpleExample(BaseExample):
+
+    text: str
+
+    def formatted(self) -> str:
+        return self.text

langchain/prompts/dynamic.py

@@ -5,7 +5,7 @@ from typing import Any, Callable, Dict, List
 from pydantic import BaseModel, Extra, root_validator
 
 from langchain.prompts.base import DEFAULT_FORMATTER_MAPPING, BasePrompt
-
+from langchain.prompts.data import BaseExample, SimpleExample
 
 class DynamicPrompt(BaseModel, BasePrompt):
     r"""Schema to represent a dynamic prompt for an LLM.
@@ -25,7 +25,7 @@ class DynamicPrompt(BaseModel, BasePrompt):
             )
     """
 
-    examples: List[str]
+    examples: List[BaseExample]
     """A list of the examples that the prompt template expects."""
 
     example_separator: str = "\n\n"
@@ -76,7 +76,7 @@ class DynamicPrompt(BaseModel, BasePrompt):
 
             prompt.format(variable1="foo")
         """
-        curr_examples = self.examples
+        curr_examples = [example.formatted for example in self.examples]
         template = self.template(curr_examples, **kwargs)
         while self.get_text_length(template) > self.max_length and curr_examples:
             curr_examples = curr_examples[:-1]
@@ -96,6 +96,16 @@ class DynamicPrompt(BaseModel, BasePrompt):
                 f"Invalid template format. Got `{template_format}`;"
                 f" should be one of {valid_formats}"
             )
+        dummy_inputs = {input_variable: "foo" for input_variable in input_variables}
+        try:
+            formatter_func = DEFAULT_FORMATTER_MAPPING[template_format]
+            formatter_func(prefix + suffix, **dummy_inputs)
+        except KeyError:
+            raise ValueError("Invalid prompt schema.")
+        return values
+
+    @root_validator()
+    def get_text_length_is_valid(cls, values: Dict) -> Dict:
         try:
             result = values["get_text_length"]("foo")
             assert isinstance(result, int)
@@ -103,10 +113,11 @@ class DynamicPrompt(BaseModel, BasePrompt):
             raise ValueError(
                 "Invalid text length callable, must take string & return int;"
             )
-        dummy_inputs = {input_variable: "foo" for input_variable in input_variables}
-        try:
-            formatter_func = DEFAULT_FORMATTER_MAPPING[template_format]
-            formatter_func(prefix + suffix, **dummy_inputs)
-        except KeyError:
-            raise ValueError("Invalid prompt schema.")
+        return values
+
+    @root_validator()
+    def convert_examples(cls, values: Dict) -> Dict:
+        examples = values["examples"]
+        examples = [example if isinstance(example, BaseExample) else SimpleExample(text=str(example)) for example in examples]
+        values["examples"] = examples
         return values