Integration: OpenStreetMap

pip install osm-integration-haystack

from osm_integration_haystack import OSMFetcher

# Create an instance of OSMFetcher
osm_fetcher = OSMFetcher(
    preset_center=(51.898403, -8.473978),  # Cork, Ireland
    preset_radius_m=500,  # 500m radius
    target_osm_types=["node"],  # Search nodes
    target_osm_tags=["amenity"],  # Search amenity types
    maximum_query_mb=2,  # Limit query size
    overpass_timeout=20
)

# Fetch nearby locations
results = osm_fetcher.run()

# Access the documents
documents = results["documents"]

print("Found locations:")
for doc in documents[:5]:  # Show first 5
    print(f"Name: {doc.meta.get('name', 'Unknown')}")
    print(f"Type: {doc.meta.get('category', 'Unknown')}")
    print(f"Distance: {doc.meta.get('distance_m', 0):.1f}m")
    print(f"Content: {doc.content}")
    print("\n")

from haystack import Pipeline
from haystack.components.builders import ChatPromptBuilder
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack.utils import Secret

# Create pipeline components
osm_fetcher = OSMFetcher(
    preset_center=(51.898403, -8.473978),  
    preset_radius_m=500,  
    target_osm_types=["node"],  
    target_osm_tags=["amenity"],  
    maximum_query_mb=2,  
    overpass_timeout=20
)

prompt_template = [
    ChatMessage.from_system(
        "You are a geographic information assistant. "
        "Based on the provided OpenStreetMap data, help the user find nearby places that match the user's query."
    ),
    ChatMessage.from_user(
        """
        User location: {{ user_location }}
        Search radius: {{ radius }}m
        User query: {{ query }}

        Available location data:
        {% for document in documents %}
        - {{ document.content }}
          Location: ({{ document.meta.lat }}, {{ document.meta.lon }})
          Distance: {{ document.meta.distance_m }}m
          Type: {{ document.meta.category }}
        {% endfor %}

        Please:
        1. Find all locations that are relevant to the user's query
        2. Sort them by distance
        3. Recommend the nearest 3 locations
        4. Provide a short description for each

        Please respond in English.
        """
    ),
]

prompt_builder = ChatPromptBuilder(
    template=prompt_template,
    required_variables=["user_location", "radius", "query", "documents"], # optional, depends on what your pipeline requires
)

llm = OpenAIChatGenerator(
    api_key=Secret.from_env_var("OPENAI_API_KEY"),
    model="gpt-4o-mini",
)

# Create and connect pipeline
coffee_pipeline = Pipeline()
coffee_pipeline.add_component("osm_fetcher", osm_fetcher)
coffee_pipeline.add_component("prompt_builder", prompt_builder)
coffee_pipeline.add_component("llm", llm)

# documents to prompt_builder
coffee_pipeline.connect("osm_fetcher.documents", "prompt_builder.documents")
# ChatPromptBuilder output toward prompt(List[ChatMessage]) as llm.messages
coffee_pipeline.connect("prompt_builder.prompt", "llm.messages")

# run the pipeline
user_location = "Cork, Ireland"
radius = 1000

result = coffee_pipeline.run(
    {
        "osm_fetcher": {},
        "prompt_builder": {
            "user_location": user_location,
            "radius": radius,
            "query": "find me the nearest coffee shop for work, needs wifi"
        },
    }
)

reply = result["llm"]["replies"][0]
print("Role:", reply.role)
print("\nAssistant reply:\n")
print(reply.text)

from osm_integration_haystack import OSMFetcher
from osm_integration_haystack.utils import GeoRadiusFilter

# First, fetch OSM data
osm_fetcher = OSMFetcher(
    preset_center=(51.898403, -8.473978),
    preset_radius_m=1000,  # Large initial radius
    target_osm_types=["node"],
    target_osm_tags=["amenity"]
)

# Get all nearby locations
results = osm_fetcher.run()
all_documents = results["documents"]

# Then apply additional radius filtering
geo_filter = GeoRadiusFilter(max_radius_m=500)  # Limit to 500m

filtered_results = geo_filter.run(
    documents=all_documents,
    center=(51.898403, -8.473978),  # Same center
    radius_m=300  # Filter to 300m radius
)

filtered_documents = filtered_results["documents"]
print(f"Filtered from {len(all_documents)} to {len(filtered_documents)} documents")

python examples/agent_osm_demo.py

# Search for coffee shops
coffee_fetcher = OSMFetcher(
    preset_center=CENTER,  # Cork, Ireland
    preset_radius_m=RADIUS_M,  # 1000m radius
    target_osm_types=["node"],  # Only search nodes
    target_osm_tags=["amenity"],  # Search amenity types
    maximum_query_mb=2,  # Limit query size
    overpass_timeout=20
)

results = coffee_fetcher.run()
documents = results["documents"]

# Filter for coffee-related locations
coffee_keywords = ["cafe", "coffee", "restaurant", "bar", "pub", "food"]
coffee_related = []

for doc in documents:
    content_lower = doc.content.lower()
    category_lower = doc.meta.get("category", "").lower()
    
    if any(keyword in content_lower or keyword in category_lower 
           for keyword in coffee_keywords):
        coffee_related.append(doc)

# Display results
for i, doc in enumerate(coffee_related[:5]):
    print(f"{i+1}. {doc.meta.get('name', 'Unknown')}")
    print(f"   Type: {doc.meta.get('category', 'Unknown')}")
    print(f"   Distance: {doc.meta.get('distance_m', 0):.1f}m")