dhisana 0.0.1.dev249__py3-none-any.whl → 0.0.1.dev251__py3-none-any.whl

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/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/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.dist-info → dhisana-0.0.1.dev251.dist-info}/METADATA

@@ -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.dist-info → dhisana-0.0.1.dev251.dist-info}/RECORD

@@ -12,10 +12,10 @@ dhisana/ui/components.py,sha256=4NXrAyl9tx2wWwoVYyABO-EOGnreGMvql1AkXWajIIo,1431
 dhisana/utils/__init__.py,sha256=jv2YF__bseklT3OWEzlqJ5qE24c4aWd5F4r0TTjOrWQ,65
 dhisana/utils/add_mapping.py,sha256=oq_QNqag86DhgdwINBRRXNx7SOb8Q9M-V0QLP6pTzr8,13837
 dhisana/utils/agent_tools.py,sha256=pzBFvfhU4wfSB4zv1eiRzjmnteJnfhC5V32r_v1m38Y,2321
-dhisana/utils/apollo_tools.py,sha256=_UDaYi_exIqe84z9Tdr1Qzn5cgYAZmK-aUwArTOTYp8,67436
+dhisana/utils/apollo_tools.py,sha256=1b9FaL_3spQKUsOP1k8-kD1kcFxCkG4KJHoN71SjOkU,69796
 dhisana/utils/assistant_tool_tag.py,sha256=rYRl8ubLI7fUUIjg30XTefHBkFgRqNEVC12lF6U6Z-8,119
 dhisana/utils/built_with_api_tools.py,sha256=TFNGhnPb2vFdveVCpjiCvE1WKe_eK95UPpR0Ha5NgMQ,10260
-dhisana/utils/cache_output_tools.py,sha256=sSAruvUZn-WAJQ0lB9T1QjSmkm-_14AuxC9xKmcCQ0k,3428
+dhisana/utils/cache_output_tools.py,sha256=q-d-WR_pkIUQyCJk8T-u9sfTy1TvvWoD2kJlZfqY-vA,4392
 dhisana/utils/cache_output_tools_local.py,sha256=okVIY54Xs5avTLu5Sv8neEPsPBce501m-6E_UhQkCAg,2447
 dhisana/utils/check_email_validity_tools.py,sha256=s2x1O3U97C4JcxIVuVh3sbgYTZzG7eGJCJT1s3NmApY,26609
 dhisana/utils/check_for_intent_signal.py,sha256=pC9k1_2fuUXBUxmikfxmoILlqhGMsJDVxrX0m73XQzA,4517
@@ -62,7 +62,7 @@ dhisana/utils/openai_helpers.py,sha256=ZK9S5-jcLCpiiD6XBLkCqYcNz-AGYmO9xh4e2H-FD
 dhisana/utils/openapi_spec_to_tools.py,sha256=oBLVq3WeDWvW9O02NCvY8bxQURQdKwHJHGcX8bC_b2I,1926
 dhisana/utils/parse_linkedin_messages_txt.py,sha256=g3N_ac70mAEuDDQ7Ott6mkOaBwI3ZvcsJD3R9RlYwPQ,3320
 dhisana/utils/profile.py,sha256=12IhefaLp3j74zzBzVRe50_KWqtWZ_cdzUKlYNy9T2Y,1192
-dhisana/utils/proxy_curl_tools.py,sha256=nHm3K_EHX8I-VGwONzCVPIA-OzbVMRXSA3VzmT_-uWk,52632
+dhisana/utils/proxy_curl_tools.py,sha256=3i7Qpk0POME5OU5-lHQ6BlnOi88tIZl-Z0oMrphnCFQ,52975
 dhisana/utils/proxycurl_search_leads.py,sha256=6PlraPNYQ4fIDzTYnY-T2g_ip5fPkqHigbGoPD8ZosQ,16131
 dhisana/utils/python_function_to_tools.py,sha256=jypddM6WTlIQmRWnqAugYJXvaPYaXaMgWAZRYeeGlj4,2682
 dhisana/utils/research_lead.py,sha256=L6w2fK5in8z2xmWnXBjbkvTdrwPf8ZfvAXq3gb7-S6s,7009
@@ -95,8 +95,8 @@ dhisana/workflow/agent.py,sha256=esv7_i_XuMkV2j1nz_UlsHov_m6X5WZZiZm_tG4OBHU,565
 dhisana/workflow/flow.py,sha256=xWE3qQbM7j2B3FH8XnY3zOL_QXX4LbTW4ArndnEYJE0,1638
 dhisana/workflow/task.py,sha256=HlWz9mtrwLYByoSnePOemBUBrMEcj7KbgNjEE1oF5wo,1830
 dhisana/workflow/test.py,sha256=E7lRnXK0PguTNzyasHytLzTJdkqIPxG5_4qk4hMEeKc,3399
-dhisana-0.0.1.dev249.dist-info/METADATA,sha256=7jNYNMhElbz3HxRJiME1__0_1sRC_IIcFkb-RnpinYc,1190
-dhisana-0.0.1.dev249.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dhisana-0.0.1.dev249.dist-info/entry_points.txt,sha256=jujxteZmNI9EkEaK-pOCoWuBujU8TCevdkfl9ZcKHek,49
-dhisana-0.0.1.dev249.dist-info/top_level.txt,sha256=NETTHt6YifG_P7XtRHbQiXZlgSFk9Qh9aR-ng1XTf4s,8
-dhisana-0.0.1.dev249.dist-info/RECORD,,
+dhisana-0.0.1.dev251.dist-info/METADATA,sha256=LbbiZTFJYpwScudL5nQgt_Seem5CqgywicGKDcJkBYI,1190
+dhisana-0.0.1.dev251.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dhisana-0.0.1.dev251.dist-info/entry_points.txt,sha256=jujxteZmNI9EkEaK-pOCoWuBujU8TCevdkfl9ZcKHek,49
+dhisana-0.0.1.dev251.dist-info/top_level.txt,sha256=NETTHt6YifG_P7XtRHbQiXZlgSFk9Qh9aR-ng1XTf4s,8
+dhisana-0.0.1.dev251.dist-info/RECORD,,