Templates (#12294)

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>

templates/stepback-qa-prompting/README.md

@@ -0,0 +1,9 @@
+# Step-Back Prompting (Question-Answering)
+
+One prompting technique called "Step-Back" prompting can improve performance on complex questions by first asking a "step back" question. This can be combined with regular question-answering applications by then doing retrieval on both the original and step-back question.
+
+Read the paper [here](https://arxiv.org/abs/2310.06117)
+
+See an excelent blog post on this by Cobus Greyling [here](https://cobusgreyling.medium.com/a-new-prompt-engineering-technique-has-been-introduced-called-step-back-prompting-b00e8954cacb)
+
+In this template we will replicate this technique. We modify the prompts used slightly to work better with chat models.

templates/stepback-qa-prompting/main.py

@@ -0,0 +1,5 @@
+from stepback_qa_prompting.chain import chain
+
+
+if __name__ == "__main__":
+    chain.invoke({"question": "was chatgpt around while trump was president?"})

templates/stepback-qa-prompting/pyproject.toml

@@ -0,0 +1,20 @@
+[tool.poetry]
+name = "stepback_qa_prompting"
+version = "0.0.1"
+description = ""
+authors = []
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313"
+duckduckgo-search = "^3.9.3"
+
+[tool.langserve]
+export_module = "stepback_qa_prompting.chain"
+export_attr = "chain"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/stepback-qa-prompting/stepback_qa_prompting/chain.py

@@ -0,0 +1,65 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableLambda
+from langchain.utilities import DuckDuckGoSearchAPIWrapper
+
+
+search = DuckDuckGoSearchAPIWrapper(max_results=4)
+
+def retriever(query):
+    return search.run(query)
+
+
+# Few Shot Examples
+examples = [
+    {
+        "input": "Could the members of The Police perform lawful arrests?",
+        "output": "what can the members of The Police do?"
+    },
+    {
+        "input": "Jan Sindel’s was born in what country?", 
+        "output": "what is Jan Sindel’s personal history?"
+    },
+]
+# We now transform these to example messages
+example_prompt = ChatPromptTemplate.from_messages(
+    [
+        ("human", "{input}"),
+        ("ai", "{output}"),
+    ]
+)
+few_shot_prompt = FewShotChatMessagePromptTemplate(
+    example_prompt=example_prompt,
+    examples=examples,
+)
+
+prompt = ChatPromptTemplate.from_messages([
+    ("system", """You are an expert at world knowledge. Your task is to step back and paraphrase a question to a more generic step-back question, which is easier to answer. Here are a few examples:"""),
+    # Few shot examples
+    few_shot_prompt,
+    # New question
+    ("user", "{question}"),
+])
+
+question_gen = prompt | ChatOpenAI(temperature=0) | StrOutputParser()
+
+response_prompt_template = """You are an expert of world knowledge. I am going to ask you a question. Your response should be comprehensive and not contradicted with the following context if they are relevant. Otherwise, ignore them if they are not relevant.
+
+{normal_context}
+{step_back_context}
+
+Original Question: {question}
+Answer:"""
+response_prompt = ChatPromptTemplate.from_template(response_prompt_template)
+
+chain = {
+    # Retrieve context using the normal question
+    "normal_context": RunnableLambda(lambda x: x['question']) | retriever,
+    # Retrieve context using the step-back question
+    "step_back_context": question_gen | retriever,
+    # Pass on the question
+    "question": lambda x: x["question"]
+} | response_prompt | ChatOpenAI(temperature=0) | StrOutputParser()
+
+