Update prompt builders examples (#6681)

haystack/components/builders/dynamic_chat_prompt_builder.py

@@ -26,13 +26,13 @@ class DynamicChatPromptBuilder:
 
     ```python
     from haystack.components.builders import DynamicChatPromptBuilder
-    from haystack.components.generators.chat import GPTChatGenerator
+    from haystack.components.generators.chat import OpenAIChatGenerator
     from haystack.dataclasses import ChatMessage
     from haystack import Pipeline
 
     # no parameter init, we don't use any runtime template variables
     prompt_builder = DynamicChatPromptBuilder()
-    llm = GPTChatGenerator(api_key="<your-api-key>", model_name="gpt-3.5-turbo")
+    llm = OpenAIChatGenerator(api_key="<your-api-key>", model_name="gpt-3.5-turbo")
 
     pipe = Pipeline()
     pipe.add_component("prompt_builder", prompt_builder)
@@ -66,7 +66,6 @@ class DynamicChatPromptBuilder:
     closer to your visit.", role=<ChatRole.ASSISTANT: 'assistant'>, name=None, meta={'model': 'gpt-3.5-turbo-0613',
     'index': 0, 'finish_reason': 'stop', 'usage': {'prompt_tokens': 37, 'completion_tokens': 201,
     'total_tokens': 238}})]}}
-
     ```
 
     The primary advantage of using DynamicChatPromptBuilder is showcased in the examples provided above.
@@ -75,10 +74,9 @@ class DynamicChatPromptBuilder:
 
     In the example above, the first query asks for general information about Berlin, and the second query requests
     the weather forecast for Berlin in the next few days. DynamicChatPromptBuilder efficiently handles these distinct
-    prompt structures by adjusting pipeline run parameters invocations, as opposed to a
+    prompt structures by adjusting pipeline run parameters invocations, as opposed to a regular PromptBuilder, which
-    regular PromptBuilder, which would require recreating or reloading the pipeline for each distinct type of query,
+    would require recreating or reloading the pipeline for each distinct type of query, leading to inefficiency and
-    leading to inefficiency and potential service disruptions, especially in server environments where continuous
+    potential service disruptions, especially in server environments where continuous service is vital.
-    service is vital.
 
     Note that the weather forecast in the example above is fictional, but it can be easily connected to a weather
     API to provide real weather forecasts.

haystack/components/builders/dynamic_prompt_builder.py

@@ -17,22 +17,21 @@ class DynamicPromptBuilder:
     The following example demonstrates how to use the DynamicPromptBuilder:
 
     ```python
+    from typing import List
     from haystack.components.builders import DynamicPromptBuilder
-    from haystack.components.generators.chat import GPTChatGenerator
+    from haystack.components.generators import OpenAIGenerator
-    from haystack.dataclasses import ChatMessage
+    from haystack import Pipeline, component, Document
-    from haystack import Pipeline
-
 
     prompt_builder = DynamicPromptBuilder(runtime_variables=["documents"])
-    llm = GPTGenerator(api_key="<your-api-key>", model_name="gpt-3.5-turbo")
+    llm = OpenAIGenerator(api_key="<your-api-key>", model_name="gpt-3.5-turbo")
 
 
     @component
     class DocumentProducer:
 
-      @component.output_types(documents=List[Document])
+        @component.output_types(documents=List[Document])
-      def run(self, doc_input: str):
+        def run(self, doc_input: str):
-        return {"documents": [Document(content=doc_input)]}
+            return {"documents": [Document(content=doc_input)]}
 
 
     pipe = Pipeline()
@@ -43,9 +42,16 @@ class DynamicPromptBuilder:
     pipe.connect("prompt_builder.prompt", "llm.prompt")
 
     template = "Here is the document: {{documents[0].content}} \\n Answer: {{query}}"
-    pipe.run(data={"doc_producer": {"doc_input": "Hello world, I live in Berlin"},
+    result = pipe.run(
-               "prompt_builder": {"prompt_source": template,
+        data={
-                                  "template_variables":{"query": "Where does the speaker live?"}}})
+            "doc_producer": {"doc_input": "Hello world, I live in Berlin"},
+            "prompt_builder": {
+                "prompt_source": template,
+                "template_variables": {"query": "Where does the speaker live?"},
+            },
+        }
+    )
+    print(result)
 
     >> {'llm': {'replies': ['The speaker lives in Berlin.'],
     >> 'meta': [{'model': 'gpt-3.5-turbo-0613',
@@ -118,8 +124,8 @@ class DynamicPromptBuilder:
                 "Please provide an appropriate template variable to enable prompt generation."
             )
 
-        template = self._validate_template(prompt_source, set(template_variables.keys()))
+        template = self._validate_template(prompt_source, set(template_variables_combined.keys()))
-        result = template.render(template_variables)
+        result = template.render(template_variables_combined)
         return {"prompt": result}
 
     def _validate_template(self, template_text: str, provided_variables: Set[str]):

test/components/builders/test_dynamic_chat_prompt_builder.py

@@ -2,6 +2,7 @@ from typing import List
 
 import pytest
 
+from haystack import Pipeline
 from haystack.components.builders import DynamicChatPromptBuilder
 from haystack.dataclasses import ChatMessage
 
@@ -90,3 +91,50 @@ class TestDynamicChatPromptBuilder:
 
         # provided variables are a superset of the required variables
         prompt_builder._validate_template("Hello, I'm {{ name }}, and I live in {{ city }}.", {"name", "city", "age"})
+
+    def test_example_in_pipeline(self):
+        # no parameter init, we don't use any runtime template variables
+        prompt_builder = DynamicChatPromptBuilder()
+
+        pipe = Pipeline()
+        pipe.add_component("prompt_builder", prompt_builder)
+
+        location = "Berlin"
+        system_message = ChatMessage.from_system(
+            "You are a helpful assistant giving out valuable information to tourists."
+        )
+        messages = [system_message, ChatMessage.from_user("Tell me about {{location}}")]
+
+        res = pipe.run(
+            data={"prompt_builder": {"template_variables": {"location": location}, "prompt_source": messages}}
+        )
+        assert res == {
+            "prompt_builder": {
+                "prompt": [
+                    ChatMessage.from_system("You are a helpful assistant giving out valuable information to tourists."),
+                    ChatMessage.from_user("Tell me about Berlin"),
+                ]
+            }
+        }
+
+        messages = [
+            system_message,
+            ChatMessage.from_user("What's the weather forecast for {{location}} in the next {{day_count}} days?"),
+        ]
+
+        res = pipe.run(
+            data={
+                "prompt_builder": {
+                    "template_variables": {"location": location, "day_count": "5"},
+                    "prompt_source": messages,
+                }
+            }
+        )
+        assert res == {
+            "prompt_builder": {
+                "prompt": [
+                    ChatMessage.from_system("You are a helpful assistant giving out valuable information to tourists."),
+                    ChatMessage.from_user("What's the weather forecast for Berlin in the next 5 days?"),
+                ]
+            }
+        }

test/components/builders/test_dynamic_prompt_builder.py

@@ -1,6 +1,9 @@
+from typing import List
+
 import pytest
 from jinja2 import TemplateSyntaxError
 
+from haystack import component, Document, Pipeline
 from haystack.components.builders import DynamicPromptBuilder
 
 
@@ -74,3 +77,34 @@ class TestDynamicPromptBuilder:
 
         # provided variables are a superset of the required variables
         prompt_builder._validate_template("Hello, I'm {{ name }}, and I live in {{ city }}.", {"name", "city", "age"})
+
+    def test_example_in_pipeline(self):
+        prompt_builder = DynamicPromptBuilder(runtime_variables=["documents"])
+
+        @component
+        class DocumentProducer:
+            @component.output_types(documents=List[Document])
+            def run(self, doc_input: str):
+                return {"documents": [Document(content=doc_input)]}
+
+        pipe = Pipeline()
+        pipe.add_component("doc_producer", DocumentProducer())
+        pipe.add_component("prompt_builder", prompt_builder)
+        pipe.connect("doc_producer.documents", "prompt_builder.documents")
+
+        template = "Here is the document: {{documents[0].content}} \\n Answer: {{query}}"
+        result = pipe.run(
+            data={
+                "doc_producer": {"doc_input": "Hello world, I live in Berlin"},
+                "prompt_builder": {
+                    "prompt_source": template,
+                    "template_variables": {"query": "Where does the speaker live?"},
+                },
+            }
+        )
+
+        assert result == {
+            "prompt_builder": {
+                "prompt": "Here is the document: Hello world, I live in Berlin \\n Answer: Where does the speaker live?"
+            }
+        }