Merge pull request #27 from reworkd/rohan

Added contact schema field descriptions

bananalyzer/data/fetch_schemas.py

@@ -1,4 +1,4 @@
-from typing import Dict, Type
+from typing import Dict, Optional, Type
 
 from pydantic import BaseModel, Field
 
@@ -8,12 +8,22 @@
 
 
 class ContactSchema(BaseModel):
-    name: str
-    phone: str
-    fax: str = Field(description="Fax number of the location")
-    address: str
-    type: str = Field(
-        description="The type of clinic the location: Hospital, Clinic, etc."
+    name: str = Field(
+        description="name of the location (not the hospital system name) *precisely* as it is written on the page (do not edit it, add text, or combine names)"
+    )
+    address: str = Field(
+        description="complete address of the location including street, city, state, and ZIP",
+    )
+    phone: str = Field(
+        description="phone number of the location (only include the number but retain its formatting)",
+    )
+    fax: Optional[str] = Field(
+        description="fax number of the location (only include the number but retain its formatting)",
+        default=None,
+    )
+    type: Optional[str] = Field(
+        description="the type of location: Neurosurgery, MRI Services, etc. (not all locations will have a type available on the page)",
+        default=None,
     )
 
 

bananalyzer/data/schemas.py

@@ -12,7 +12,7 @@
 
 GoalType = Literal[
     "fetch",  # Scrape specific JSON information from a single page. Does not require navigation
-    "links",  # Scrape all detail page links from a single page
+    "links",  # Scrape all detail page links from a single listing page
     "click",  # Make a single click on a page
     "navigate",  # Travel to a new page
     "search",  # Search for the answer to a specific query