web_questions.py

from haystack import Pipeline
from haystack.components.builders import PromptBuilder
from haystack.components.converters import HTMLToDocument
from haystack.components.fetchers import LinkContentFetcher
from haystack.components.generators import OpenAIGenerator
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

from openinference.instrumentation.haystack import HaystackInstrumentor

# Configure HaystackInstrumentor with Phoenix endpoint
endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))

HaystackInstrumentor().instrument(tracer_provider=tracer_provider)


fetcher = LinkContentFetcher()
converter = HTMLToDocument()
prompt_template = """
According to the contents of this website:
{% for document in documents %}
  {{document.content}}
{% endfor %}
Answer the given question: {{query}}
Answer:
"""
prompt_builder = PromptBuilder(template=prompt_template)
llm = OpenAIGenerator()

pipeline = Pipeline()
pipeline.add_component("fetcher", fetcher)
pipeline.add_component("converter", converter)
pipeline.add_component("prompt", prompt_builder)
pipeline.add_component("llm", llm)

pipeline.connect("fetcher.streams", "converter.sources")
pipeline.connect("converter.documents", "prompt.documents")
pipeline.connect("prompt.prompt", "llm.prompt")

result = pipeline.run(
    {
        "fetcher": {"urls": ["https://haystack.deepset.ai/overview/quick-start"]},
        "prompt": {"query": "Which components do I need for a RAG pipeline?"},
    }
)

print(result["llm"]["replies"][0])