my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	name: local-places
#3	description: Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
#4	homepage: https://github.com/Hyaxia/local_places
#5	metadata: {"clawdbot":{"emoji":"📍","requires":{"bins":["uv"],"env":["GOOGLE_PLACES_API_KEY"]},"primaryEnv":"GOOGLE_PLACES_API_KEY"}}
#6	---
#7
#8	# 📍 Local Places
#9
#10	Find places, Go fast
#11
#12	Search for nearby places using a local Google Places API proxy. Two-step flow: resolve location first, then search.
#13
#14	## Setup
#15
#16	```bash
#17	cd {baseDir}
#18	echo "GOOGLE_PLACES_API_KEY=your-key" > .env
#19	uv venv && uv pip install -e ".[dev]"
#20	uv run --env-file .env uvicorn local_places.main:app --host 127.0.0.1 --port 8000
#21	```
#22
#23	Requires `GOOGLE_PLACES_API_KEY` in `.env` or environment.
#24
#25	## Quick Start
#26
#27	1. Check server: `curl http://127.0.0.1:8000/ping`
#28
#29	2. Resolve location:
#30	```bash
#31	curl -X POST http://127.0.0.1:8000/locations/resolve \
#32	-H "Content-Type: application/json" \
#33	-d '{"location_text": "Soho, London", "limit": 5}'
#34	```
#35
#36	3. Search places:
#37	```bash
#38	curl -X POST http://127.0.0.1:8000/places/search \
#39	-H "Content-Type: application/json" \
#40	-d '{
#41	"query": "coffee shop",
#42	"location_bias": {"lat": 51.5137, "lng": -0.1366, "radius_m": 1000},
#43	"filters": {"open_now": true, "min_rating": 4.0},
#44	"limit": 10
#45	}'
#46	```
#47
#48	4. Get details:
#49	```bash
#50	curl http://127.0.0.1:8000/places/{place_id}
#51	```
#52
#53	## Conversation Flow
#54
#55	1. If user says "near me" or gives vague location → resolve it first
#56	2. If multiple results → show numbered list, ask user to pick
#57	3. Ask for preferences: type, open now, rating, price level
#58	4. Search with `location_bias` from chosen location
#59	5. Present results with name, rating, address, open status
#60	6. Offer to fetch details or refine search
#61
#62	## Filter Constraints
#63
#64	- `filters.types`: exactly ONE type (e.g., "restaurant", "cafe", "gym")
#65	- `filters.price_levels`: integers 0-4 (0=free, 4=very expensive)
#66	- `filters.min_rating`: 0-5 in 0.5 increments
#67	- `filters.open_now`: boolean
#68	- `limit`: 1-20 for search, 1-10 for resolve
#69	- `location_bias.radius_m`: must be > 0
#70
#71	## Response Format
#72
#73	```json
#74	{
#75	"results": [
#76	{
#77	"place_id": "ChIJ...",
#78	"name": "Coffee Shop",
#79	"address": "123 Main St",
#80	"location": {"lat": 51.5, "lng": -0.1},
#81	"rating": 4.6,
#82	"price_level": 2,
#83	"types": ["cafe", "food"],
#84	"open_now": true
#85	}
#86	],
#87	"next_page_token": "..."
#88	}
#89	```
#90
#91	Use `next_page_token` as `page_token` in next request for more results.
#92

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public