dhisana 0.0.1.dev249__tar.gz → 0.0.1.dev251__tar.gz

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dhisana
-Version: 0.0.1.dev249
+Version: 0.0.1.dev251
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='dhisana',  
-    version='0.0.1-dev249',
+    version='0.0.1-dev251',
     description='A Python SDK for Dhisana AI Platform',
     author='Admin',
     author_email='contact@dhisana.ai',

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/src/dhisana/utils/apollo_tools.py

@@ -1287,62 +1287,131 @@ def fill_in_company_properties(company_data: dict) -> dict:
         company_data: Raw company data from Apollo API
         
     Returns:
-        Dictionary with standardized company properties
+        Dictionary matching the SmartList `Account` schema shape.
     """
-    company_properties = {}
+    def _parse_keywords(value: Any) -> List[Any]:
+        if value is None:
+            return []
+        if isinstance(value, list):
+            return value
+        if isinstance(value, str):
+            text = value.strip()
+            if not text:
+                return []
+            if "," in text:
+                return [part.strip() for part in text.split(",") if part.strip()]
+            return [text]
+        return [value]
 
-    # Basic company information
-    company_properties["organization_name"] = company_data.get("name", "")
-    company_properties["primary_domain"] = company_data.get("primary_domain", "")
-    company_properties["website_url"] = company_data.get("website_url", "")
-    company_properties["organization_linkedin_url"] = company_data.get("linkedin_url", "")
-    
-    # Location information
-    company_properties["organization_city"] = company_data.get("city", "")
-    company_properties["organization_state"] = company_data.get("state", "")
-    company_properties["organization_country"] = company_data.get("country", "")
-    
-    # Create a combined location string
-    location_parts = [
-        company_data.get("city", ""),
-        company_data.get("state", ""),
-        company_data.get("country", "")
-    ]
-    company_properties["organization_location"] = ", ".join([part for part in location_parts if part])
-
-    # Company size and financial info
-    company_properties["employee_count"] = company_data.get("estimated_num_employees", 0)
-    company_properties["annual_revenue"] = company_data.get("annual_revenue", 0)
-    
-    # Industry and business info
-    company_properties["industry"] = company_data.get("industry", "")
-    company_properties["keywords"] = ", ".join(company_data.get("keywords", []))
-    company_properties["description"] = company_data.get("description", "")
-    
-    # Funding and growth
-    company_properties["founded_year"] = company_data.get("founded_year", "")
-    company_properties["funding_stage"] = company_data.get("latest_funding_stage", "")
-    company_properties["total_funding"] = company_data.get("total_funding", 0)
-    
-    # Technology stack
-    tech_stack = company_data.get("technology_names", [])
-    if tech_stack:
-        company_properties["technology_stack"] = ", ".join(tech_stack)
-    
-    # Apollo-specific IDs
-    company_properties["apollo_organization_id"] = company_data.get("id", "")
-    
-    # Additional metadata
-    company_properties["phone"] = company_data.get("phone", "")
-    company_properties["facebook_url"] = company_data.get("facebook_url", "")
-    company_properties["twitter_url"] = company_data.get("twitter_url", "")
-    
-    # Store raw data for reference
-    company_properties["additional_properties"] = {
-        "apollo_organization_data": json.dumps(cleanup_properties(company_data))
+    def _parse_compact_number(value: Any) -> Optional[float]:
+        if value is None:
+            return None
+        if isinstance(value, (int, float)):
+            return float(value)
+        text = str(value).strip()
+        if not text:
+            return None
+        text = text.replace("$", "").replace(",", "").strip()
+        multiplier = 1.0
+        suffix = text[-1:].upper()
+        if suffix in ("K", "M", "B"):
+            multiplier = {"K": 1e3, "M": 1e6, "B": 1e9}[suffix]
+            text = text[:-1].strip()
+        try:
+            return float(text) * multiplier
+        except ValueError:
+            return None
+
+    annual_revenue = (
+        company_data.get("organization_revenue")
+        if company_data.get("organization_revenue") is not None
+        else company_data.get("annual_revenue")
+    )
+    annual_revenue = _parse_compact_number(annual_revenue)
+    if annual_revenue is None:
+        annual_revenue = _parse_compact_number(company_data.get("organization_revenue_printed"))
+
+    company_size = company_data.get("estimated_num_employees")
+    if company_size is not None:
+        try:
+            company_size = int(company_size)
+        except (TypeError, ValueError):
+            company_size = None
+
+    founded_year = company_data.get("founded_year")
+    if founded_year is not None:
+        try:
+            founded_year = int(founded_year)
+        except (TypeError, ValueError):
+            founded_year = None
+
+    primary_phone = company_data.get("primary_phone")
+    primary_phone_number = None
+    if isinstance(primary_phone, dict):
+        primary_phone_number = primary_phone.get("number") or primary_phone.get(
+            "sanitized_number"
+        )
+
+    phone = (
+        primary_phone_number
+        or company_data.get("phone")
+        or company_data.get("primary_phone_number")
+        or company_data.get("sanitized_phone")
+    )
+
+    industry = company_data.get("industry")
+    if not industry and isinstance(company_data.get("industries"), list):
+        industries = [str(x).strip() for x in company_data["industries"] if str(x).strip()]
+        industry = industries[0] if industries else None
+
+    billing_street = (
+        company_data.get("street_address")
+        or company_data.get("billing_street")
+        or company_data.get("address")
+        or company_data.get("raw_address")
+    )
+
+    account: Dict[str, Any] = {
+        "name": company_data.get("name"),
+        "domain": company_data.get("primary_domain"),
+        "website": company_data.get("website_url"),
+        "phone": phone,
+        "fax": company_data.get("fax") or company_data.get("fax_number"),
+        "industry": industry,
+        "company_size": company_size,
+        "founded_year": founded_year,
+        "annual_revenue": annual_revenue,
+        "type": company_data.get("type") or company_data.get("organization_type"),
+        "ownership": company_data.get("ownership"),
+        "organization_linkedin_url": company_data.get("linkedin_url"),
+        "billing_street": billing_street,
+        "billing_city": company_data.get("city"),
+        "billing_state": company_data.get("state"),
+        "billing_zip": company_data.get("postal_code")
+        or company_data.get("zip")
+        or company_data.get("zipcode"),
+        "billing_country": company_data.get("country"),
+        "description": company_data.get("description"),
+        "keywords": _parse_keywords(company_data.get("keywords")),
+        "tags": [],
+        "notes": [],
+        "additional_properties": {
+            "apollo_organization_id": company_data.get("id"),
+            "facebook_url": company_data.get("facebook_url"),
+            "twitter_url": company_data.get("twitter_url"),
+            "funding_stage": company_data.get("latest_funding_stage"),
+            "total_funding": company_data.get("total_funding"),
+            "technology_names": company_data.get("technology_names"),
+            "primary_phone": primary_phone if isinstance(primary_phone, dict) else None,
+            "raw_address": company_data.get("raw_address"),
+            "organization_revenue_printed": company_data.get("organization_revenue_printed"),
+            "apollo_organization_data": json.dumps(cleanup_properties(company_data)),
+        },
+        "research_summary": None,
+        "enchrichment_status": None,
     }
 
-    return company_properties
+    return account
 
 
 @assistant_tool

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/src/dhisana/utils/cache_output_tools.py

@@ -2,6 +2,7 @@ import os
 import hashlib
 import json
 import logging
+from datetime import datetime, timezone
 
 from azure.storage.blob import BlobServiceClient
 from azure.core.exceptions import ResourceNotFoundError, AzureError
@@ -49,10 +50,11 @@ def cache_output(tool_name: str, key: str, value, ttl: int = None) -> bool:
     # Construct the blob name using a virtual folder for the tool name
     blob_name = f"{tool_name}/{key_hash}.json"
 
-    # Prepare the cache data
+    # Prepare the cache data with timestamp for TTL expiration checking
     cache_data = {
         "value": value,
-        "ttl": ttl
+        "ttl": ttl,
+        "cached_at": datetime.now(timezone.utc).isoformat()
     }
     data = json.dumps(cache_data)
 
@@ -88,6 +90,24 @@ def retrieve_output(tool_name: str, key: str):
         download_stream = blob_client.download_blob()
         content = download_stream.readall()  # content is in bytes
         cache_data = json.loads(content.decode("utf-8"))
+        
+        # Check if TTL has expired
+        ttl = cache_data.get("ttl")
+        cached_at = cache_data.get("cached_at")
+        
+        if ttl is not None and cached_at is not None:
+            try:
+                cached_time = datetime.fromisoformat(cached_at)
+                now = datetime.now(timezone.utc)
+                elapsed_seconds = (now - cached_time).total_seconds()
+                if elapsed_seconds > ttl:
+                    logger.info(f"Cache expired for blob '{blob_name}' (elapsed: {elapsed_seconds}s, ttl: {ttl}s)")
+                    return None
+            except (ValueError, TypeError) as e:
+                logger.warning(f"Error parsing cached_at timestamp: {e}")
+                # If we can't parse the timestamp, treat as expired for safety
+                return None
+        
         return cache_data.get("value")
     except ResourceNotFoundError:
         # Blob does not exist

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/src/dhisana/utils/proxy_curl_tools.py

@@ -16,6 +16,9 @@ from urllib.parse import urlparse, urlunparse
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
+# Cache TTL for Proxycurl responses: 14 days in seconds
+PROXYCURL_CACHE_TTL = 14 * 24 * 60 * 60  # 1,209,600 seconds
+
 
 def get_proxycurl_access_token(tool_config: Optional[List[Dict]] = None) -> str:
     """
@@ -117,7 +120,7 @@ async def enrich_person_info_from_proxycurl(
                 if response.status == 200:
                     result = await response.json()
                     if linkedin_url:
-                        cache_output("enrich_person_info_from_proxycurl", linkedin_url, result)
+                        cache_output("enrich_person_info_from_proxycurl", linkedin_url, result, ttl=PROXYCURL_CACHE_TTL)
                     logger.info("Successfully retrieved person info from Proxycurl.")
                     return result
                 elif response.status == 404:
@@ -195,14 +198,14 @@ async def lookup_person_in_proxy_curl_by_name(
                 logger.debug(f"Received response status: {response.status}")
                 if response.status == 200:
                     result = await response.json()
-                    cache_output("lookup_person_in_proxycurl_by_name", key, result)
+                    cache_output("lookup_person_in_proxycurl_by_name", key, result, ttl=PROXYCURL_CACHE_TTL)
                     logger.info("Successfully retrieved person search info from Proxycurl.")
                     return result
                 elif response.status == 404:
                     msg = "Person not found"
                     logger.warning(msg)
                     if key:
-                        cache_output("lookup_person_in_proxycurl_by_name", key, {'error': msg})
+                        cache_output("lookup_person_in_proxycurl_by_name", key, {'error': msg}, ttl=PROXYCURL_CACHE_TTL)
                     return {'error': msg}
                 elif response.status == 429:
                     msg = "Rate limit exceeded"
@@ -415,7 +418,7 @@ async def enrich_organization_info_from_proxycurl(
                     if response.status == 200:
                         result = await response.json()
                         transformed_result = transform_company_data(result)
-                        cache_output("enrich_organization_info_from_proxycurl", cache_key, transformed_result)
+                        cache_output("enrich_organization_info_from_proxycurl", cache_key, transformed_result, ttl=PROXYCURL_CACHE_TTL)
                         logger.info("Successfully retrieved and transformed organization info from Proxycurl by LinkedIn URL.")
                         return transformed_result
                     elif response.status == 429:
@@ -429,7 +432,7 @@ async def enrich_organization_info_from_proxycurl(
                             f"Proxycurl organization profile not found for LinkedIn URL {standardized_url}: {error_text}"
                         )
                         cache_output(
-                            "enrich_organization_info_from_proxycurl", cache_key, {}
+                            "enrich_organization_info_from_proxycurl", cache_key, {}, ttl=PROXYCURL_CACHE_TTL
                         )
                         return {}
                     else:
@@ -483,7 +486,7 @@ async def enrich_organization_info_from_proxycurl(
                                     if profile_response.status == 200:
                                         result = await profile_response.json()
                                         transformed_result = transform_company_data(result)
-                                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, transformed_result)
+                                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, transformed_result, ttl=PROXYCURL_CACHE_TTL)
                                         logger.info("Successfully retrieved and transformed organization info from Proxycurl by domain.")
                                         return transformed_result
                                     elif profile_response.status == 429:
@@ -509,7 +512,7 @@ async def enrich_organization_info_from_proxycurl(
                     elif response.status == 404:
                         msg = "Item not found"
                         logger.warning(msg)
-                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, {})
+                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, {}, ttl=PROXYCURL_CACHE_TTL)
                         return {}
                     else:
                         error_text = await response.text()
@@ -572,7 +575,7 @@ async def enrich_job_info_from_proxycurl(
                 logger.debug(f"Received response status: {response.status}")
                 if response.status == 200:
                     result = await response.json()
-                    cache_output("enrich_job_info_from_proxycurl", job_url, result)
+                    cache_output("enrich_job_info_from_proxycurl", job_url, result, ttl=PROXYCURL_CACHE_TTL)
                     logger.info("Successfully retrieved job info from Proxycurl.")
                     return result
                 elif response.status == 429:
@@ -583,7 +586,7 @@ async def enrich_job_info_from_proxycurl(
                 elif response.status == 404:
                     msg = "Job not found"
                     logger.warning(msg)
-                    cache_output("enrich_job_info_from_proxycurl", job_url, {'error': msg})
+                    cache_output("enrich_job_info_from_proxycurl", job_url, {'error': msg}, ttl=PROXYCURL_CACHE_TTL)
                     return {'error': msg}
                 else:
                     error_text = await response.text()

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/src/dhisana.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dhisana
-Version: 0.0.1.dev249
+Version: 0.0.1.dev251
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin

{dhisana-0.0.1.dev249 → dhisana-0.0.1.dev251}/tests/test_apollo_company_search.py

@@ -84,31 +84,37 @@ class TestApolloCompanySearch(unittest.IsolatedAsyncioTestCase):
         company_data = self.mock_apollo_response["organizations"][0]
         result = fill_in_company_properties(company_data)
         
-        self.assertEqual(result["organization_name"], "Example Corp")
-        self.assertEqual(result["primary_domain"], "example.com")
-        self.assertEqual(result["website_url"], "https://example.com")
-        self.assertEqual(result["organization_linkedin_url"], "https://linkedin.com/company/example-corp")
-        self.assertEqual(result["organization_city"], "San Francisco")
-        self.assertEqual(result["organization_state"], "California")
-        self.assertEqual(result["organization_country"], "United States")
-        self.assertEqual(result["organization_location"], "San Francisco, California, United States")
-        self.assertEqual(result["employee_count"], 150)
-        self.assertEqual(result["annual_revenue"], 10000000)
+        self.assertEqual(result["name"], "Example Corp")
+        self.assertEqual(result["domain"], "example.com")
+        self.assertEqual(result["website"], "https://example.com")
+        self.assertEqual(
+            result["organization_linkedin_url"],
+            "https://linkedin.com/company/example-corp",
+        )
+        self.assertEqual(result["billing_city"], "San Francisco")
+        self.assertEqual(result["billing_state"], "California")
+        self.assertEqual(result["billing_country"], "United States")
+        self.assertEqual(result["company_size"], 150)
+        self.assertEqual(result["annual_revenue"], 10000000.0)
         self.assertEqual(result["industry"], "Technology")
-        self.assertEqual(result["keywords"], "saas, software")
+        self.assertEqual(result["keywords"], ["saas", "software"])
         self.assertEqual(result["description"], "A technology company")
         self.assertEqual(result["founded_year"], 2010)
-        self.assertEqual(result["funding_stage"], "Series B")
-        self.assertEqual(result["total_funding"], 5000000)
-        self.assertEqual(result["technology_stack"], "React, Python, AWS")
-        self.assertEqual(result["apollo_organization_id"], "123456")
         self.assertEqual(result["phone"], "+1-555-123-4567")
-        self.assertEqual(result["facebook_url"], "https://facebook.com/example-corp")
-        self.assertEqual(result["twitter_url"], "https://twitter.com/example_corp")
         
         # Check that additional_properties contains the raw data
         self.assertIn("additional_properties", result)
         self.assertIn("apollo_organization_data", result["additional_properties"])
+        self.assertEqual(result["additional_properties"]["apollo_organization_id"], "123456")
+        self.assertEqual(
+            result["additional_properties"]["facebook_url"], "https://facebook.com/example-corp"
+        )
+        self.assertEqual(
+            result["additional_properties"]["twitter_url"], "https://twitter.com/example_corp"
+        )
+        self.assertEqual(result["additional_properties"]["funding_stage"], "Series B")
+        self.assertEqual(result["additional_properties"]["total_funding"], 5000000)
+        self.assertEqual(result["additional_properties"]["technology_names"], ["React", "Python", "AWS"])
 
     @patch('src.dhisana.utils.apollo_tools.fetch_apollo_data')
     @patch('src.dhisana.utils.apollo_tools.get_apollo_access_token')
@@ -141,8 +147,8 @@ class TestApolloCompanySearch(unittest.IsolatedAsyncioTestCase):
         
         # Check results
         self.assertEqual(len(result["results"]), 2)
-        self.assertEqual(result["results"][0]["organization_name"], "Example Corp")
-        self.assertEqual(result["results"][1]["organization_name"], "Test Inc")
+        self.assertEqual(result["results"][0]["name"], "Example Corp")
+        self.assertEqual(result["results"][1]["name"], "Test Inc")
         
         # Verify API call was made correctly
         mock_fetch_data.assert_called_once()
@@ -207,6 +213,22 @@ class TestApolloCompanySearch(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(query.sort_by_field, "employee_count")
         self.assertFalse(query.sort_ascending)
 
+    def test_fill_in_company_properties_prefers_primary_phone_and_org_revenue(self):
+        company_data = dict(self.mock_apollo_response["organizations"][0])
+        company_data["primary_phone"] = {
+            "number": "+971 4 433 2589",
+            "source": "Account",
+            "sanitized_number": "+97144332589",
+        }
+        company_data.pop("annual_revenue", None)
+        company_data["organization_revenue_printed"] = "35M"
+        company_data["organization_revenue"] = 35000000.0
+
+        result = fill_in_company_properties(company_data)
+        self.assertEqual(result["phone"], "+971 4 433 2589")
+        self.assertEqual(result["annual_revenue"], 35000000.0)
+        self.assertEqual(result["additional_properties"]["organization_revenue_printed"], "35M")
+
     @patch('src.dhisana.utils.apollo_tools.fetch_apollo_data')
     @patch('src.dhisana.utils.apollo_tools.get_apollo_access_token')
     async def test_search_companies_with_apollo_basic(self, mock_get_token, mock_fetch_data):