dhisana 0.0.1.dev235__tar.gz → 0.0.1.dev236__tar.gz

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dhisana
-Version: 0.0.1.dev235
+Version: 0.0.1.dev236
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='dhisana',  
-    version='0.0.1-dev235',
+    version='0.0.1-dev236',
     description='A Python SDK for Dhisana AI Platform',
     author='Admin',
     author_email='contact@dhisana.ai',

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/src/dhisana/utils/enrich_lead_information.py

@@ -765,16 +765,32 @@ async def enrich_organization_info_from_company_url(
     organization_linkedin_url: str,
     use_strict_check: bool = True,
     tool_config: Optional[List[Dict[str, Any]]] = None,
+    categories: Optional[bool] = None,
+    funding_data: Optional[bool] = None,
+    exit_data: Optional[bool] = None,
+    acquisitions: Optional[bool] = None,
+    extra: Optional[bool] = None,
+    use_cache: Optional[str] = "if-present",
+    fallback_to_cache: Optional[str] = "on-error",
 ) -> Dict[str, Any]:
     """
     Given an organization LinkedIn URL, attempt to enrich its data (e.g. name, website)
-    via ProxyCurl. If data is found, set domain, then return the dict. Otherwise, return {}.
+    via ProxyCurl. Additional Proxycurl Company API boolean flags (categories, funding_data, etc.)
+    can be supplied to control the returned payload (True -> "include"). If data is found,
+    set domain, then return the dict. Otherwise, return {}.
     """
 
     # Call ProxyCurl to enrich
     company_data = await enrich_organization_info_from_proxycurl(
         organization_linkedin_url=organization_linkedin_url,
-        tool_config=tool_config
+        tool_config=tool_config,
+        categories=categories,
+        funding_data=funding_data,
+        exit_data=exit_data,
+        acquisitions=acquisitions,
+        extra=extra,
+        use_cache=use_cache,
+        fallback_to_cache=fallback_to_cache,
     )
 
     # If ProxyCurl returned any data, set domain, then return

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/src/dhisana/utils/google_oauth_tools.py

@@ -194,46 +194,62 @@ async def list_emails_in_time_range_google_oauth_async(
         q_parts.extend([f"label:{lbl}" for lbl in context.labels])
     query = " ".join(q_parts)
 
-    params = {"q": query}
+    params = {"q": query, "maxResults": 100}
 
     items: List[MessageItem] = []
+    max_fetch = 500  # defensive cap to avoid excessive paging
     async with httpx.AsyncClient(timeout=30) as client:
         try:
-            list_resp = await client.get(base_url, headers=headers, params=params)
-            list_resp.raise_for_status()
-            list_data = list_resp.json() or {}
-            for m in list_data.get("messages", []) or []:
-                mid = m.get("id")
-                tid = m.get("threadId")
-                if not mid:
-                    continue
-                get_url = f"{base_url}/{mid}"
-                get_resp = await client.get(get_url, headers=headers)
-                get_resp.raise_for_status()
-                mdata = get_resp.json() or {}
-
-                headers_list = (mdata.get("payload") or {}).get("headers", [])
-                from_header = find_header(headers_list, "From") or ""
-                subject_header = find_header(headers_list, "Subject") or ""
-                date_header = find_header(headers_list, "Date") or ""
-
-                iso_dt = convert_date_to_iso(date_header)
-                s_name, s_email = parse_single_address(from_header)
-                r_name, r_email = find_all_recipients_in_headers(headers_list)
-
-                items.append(
-                    MessageItem(
-                        message_id=mdata.get("id", ""),
-                        thread_id=tid or "",
-                        sender_name=s_name,
-                        sender_email=s_email,
-                        receiver_name=r_name,
-                        receiver_email=r_email,
-                        iso_datetime=iso_dt,
-                        subject=subject_header,
-                        body=extract_email_body_in_plain_text(mdata),
+            next_page_token = None
+            while True:
+                page_params = dict(params)
+                if next_page_token:
+                    page_params["pageToken"] = next_page_token
+
+                list_resp = await client.get(base_url, headers=headers, params=page_params)
+                list_resp.raise_for_status()
+                list_data = list_resp.json() or {}
+                for m in list_data.get("messages", []) or []:
+                    if len(items) >= max_fetch:
+                        break
+                    mid = m.get("id")
+                    tid = m.get("threadId")
+                    if not mid:
+                        continue
+                    get_url = f"{base_url}/{mid}"
+                    get_resp = await client.get(get_url, headers=headers)
+                    get_resp.raise_for_status()
+                    mdata = get_resp.json() or {}
+
+                    headers_list = (mdata.get("payload") or {}).get("headers", [])
+                    from_header = find_header(headers_list, "From") or ""
+                    subject_header = find_header(headers_list, "Subject") or ""
+                    date_header = find_header(headers_list, "Date") or ""
+
+                    iso_dt = convert_date_to_iso(date_header)
+                    s_name, s_email = parse_single_address(from_header)
+                    r_name, r_email = find_all_recipients_in_headers(headers_list)
+
+                    items.append(
+                        MessageItem(
+                            message_id=mdata.get("id", ""),
+                            thread_id=tid or "",
+                            sender_name=s_name,
+                            sender_email=s_email,
+                            receiver_name=r_name,
+                            receiver_email=r_email,
+                            iso_datetime=iso_dt,
+                            subject=subject_header,
+                            body=extract_email_body_in_plain_text(mdata),
+                        )
                     )
-                )
+
+                if len(items) >= max_fetch:
+                    break
+
+                next_page_token = list_data.get("nextPageToken")
+                if not next_page_token:
+                    break
         except httpx.HTTPStatusError as exc:
             _rethrow_with_google_message(exc, "Gmail List OAuth")
 

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/src/dhisana/utils/google_workspace_tools.py

@@ -241,47 +241,64 @@ async def list_emails_in_time_range_async(
         query += f' {label_query}'
 
     headers = {'Authorization': f'Bearer {access_token}'}
-    params = {'q': query}
+    params = {'q': query, 'maxResults': 100}
 
     message_items: List[MessageItem] = []
+    max_fetch = 500  # defensive cap
     async with httpx.AsyncClient() as client:
-        response = await client.get(gmail_api_url, headers=headers, params=params)
-        response.raise_for_status()
-        messages = response.json().get('messages', [])
-
-        for msg in messages:
-            message_id = msg['id']
-            thread_id = msg['threadId']
-            message_url = f'{gmail_api_url}/{message_id}'
-            message_response = await client.get(message_url, headers=headers)
-            message_response.raise_for_status()
-            message_data = message_response.json()
-
-            headers_list = message_data['payload']['headers']
-            from_header = find_header(headers_list, 'From') or ""
-            subject_header = find_header(headers_list, 'Subject') or ""
-            date_header = find_header(headers_list, 'Date') or ""
-
-            iso_datetime_str = convert_date_to_iso(date_header)
+        next_page_token = None
+        while True:
+            page_params = dict(params)
+            if next_page_token:
+                page_params["pageToken"] = next_page_token
 
-            # Parse the "From" into (sender_name, sender_email)
-            s_name, s_email = parse_single_address(from_header)
+            response = await client.get(gmail_api_url, headers=headers, params=page_params)
+            response.raise_for_status()
+            resp_json = response.json() or {}
+            messages = resp_json.get('messages', [])
+
+            for msg in messages:
+                if len(message_items) >= max_fetch:
+                    break
+                message_id = msg['id']
+                thread_id = msg.get('threadId', "")
+                message_url = f'{gmail_api_url}/{message_id}'
+                message_response = await client.get(message_url, headers=headers)
+                message_response.raise_for_status()
+                message_data = message_response.json()
+
+                headers_list = message_data['payload']['headers']
+                from_header = find_header(headers_list, 'From') or ""
+                subject_header = find_header(headers_list, 'Subject') or ""
+                date_header = find_header(headers_list, 'Date') or ""
+
+                iso_datetime_str = convert_date_to_iso(date_header)
+
+                # Parse the "From" into (sender_name, sender_email)
+                s_name, s_email = parse_single_address(from_header)
+
+                # Parse the recipients
+                r_name, r_email = find_all_recipients_in_headers(headers_list)
+
+                msg_item = MessageItem(
+                    message_id=message_data['id'],                
+                    thread_id=thread_id,
+                    sender_name=s_name,
+                    sender_email=s_email,
+                    receiver_name=r_name,
+                    receiver_email=r_email,
+                    iso_datetime=iso_datetime_str,
+                    subject=subject_header,
+                    body=extract_email_body_in_plain_text(message_data)
+                )
+                message_items.append(msg_item)
 
-            # Parse the recipients
-            r_name, r_email = find_all_recipients_in_headers(headers_list)
+            if len(message_items) >= max_fetch:
+                break
 
-            msg_item = MessageItem(
-                message_id=message_data['id'],                
-                thread_id=thread_id,
-                sender_name=s_name,
-                sender_email=s_email,
-                receiver_name=r_name,
-                receiver_email=r_email,
-                iso_datetime=iso_datetime_str,
-                subject=subject_header,
-                body=extract_email_body_in_plain_text(message_data)
-            )
-            message_items.append(msg_item)
+            next_page_token = resp_json.get("nextPageToken")
+            if not next_page_token:
+                break
 
     return message_items
 

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/src/dhisana/utils/proxy_curl_tools.py

@@ -273,6 +273,46 @@ def transform_company_data(data: dict) -> dict:
     return transformed
 
 
+def _build_company_profile_params(
+    company_url: str,
+    profile_flags: Dict[str, Optional[str]],
+) -> Dict[str, str]:
+    """
+    Build request params for the Enrichlayer company profile endpoint,
+    ensuring we only forward flags that were explicitly provided.
+    """
+    params: Dict[str, str] = {'url': company_url}
+    for key, value in profile_flags.items():
+        if value is not None:
+            params[key] = value
+    return params
+
+
+def _build_company_cache_key(identifier: str, profile_flags: Dict[str, Optional[str]]) -> str:
+    """
+    Builds a cache key that is unique for the combination of identifier
+    (LinkedIn URL or domain) and the optional enrichment flags.
+    """
+    suffix_bits = [
+        f"{key}={value}"
+        for key, value in sorted(profile_flags.items())
+        if value is not None
+    ]
+    if suffix_bits:
+        return f"{identifier}|{'&'.join(suffix_bits)}"
+    return identifier
+
+
+def _bool_to_include_exclude(value: Optional[bool]) -> Optional[str]:
+    """
+    Convert a boolean flag into the string literals expected by Proxycurl.
+    True -> "include", False -> "exclude", None -> None (omit parameter).
+    """
+    if value is None:
+        return None
+    return "include" if value else "exclude"
+
+
 @backoff.on_exception(
     backoff.expo,
     aiohttp.ClientResponseError,
@@ -283,10 +323,27 @@ def transform_company_data(data: dict) -> dict:
 async def enrich_organization_info_from_proxycurl(
     organization_domain: Optional[str] = None,
     organization_linkedin_url: Optional[str] = None,
-    tool_config: Optional[List[Dict]] = None
+    tool_config: Optional[List[Dict]] = None,
+    categories: Optional[bool] = None,
+    funding_data: Optional[bool] = None,
+    exit_data: Optional[bool] = None,
+    acquisitions: Optional[bool] = None,
+    extra: Optional[bool] = None,
+    use_cache: Optional[str] = "if-present",
+    fallback_to_cache: Optional[str] = "on-error",
 ) -> Dict:
     """
     Fetch an organization's details from Proxycurl using either the organization domain or LinkedIn URL.
+    Additional keyword parameters map directly to the Enrichlayer Company Profile endpoint.
+    
+    Args:
+        organization_domain: Organization's domain name to resolve via Proxycurl.
+        organization_linkedin_url: LinkedIn company profile URL.
+        tool_config: Optional tool configuration metadata for credential lookup.
+        categories/funding_data/exit_data/acquisitions/extra: Set True to request
+            "include", False for "exclude", or None to omit.
+        use_cache: Controls Proxycurl caching behaviour (e.g. "if-present").
+        fallback_to_cache: Controls Proxycurl cache fallback behaviour (e.g. "on-error").
     
     Returns:
         dict: Transformed JSON response containing organization information,
@@ -308,6 +365,16 @@ async def enrich_organization_info_from_proxycurl(
         logger.warning("No organization domain or LinkedIn URL provided.")
         return {}
 
+    profile_flags: Dict[str, Optional[str]] = {
+        "categories": _bool_to_include_exclude(categories),
+        "funding_data": _bool_to_include_exclude(funding_data),
+        "exit_data": _bool_to_include_exclude(exit_data),
+        "acquisitions": _bool_to_include_exclude(acquisitions),
+        "extra": _bool_to_include_exclude(extra),
+        "use_cache": use_cache,
+        "fallback_to_cache": fallback_to_cache,
+    }
+
     # If LinkedIn URL is provided, standardize it and fetch data
     if organization_linkedin_url:
         logger.debug(f"Organization LinkedIn URL provided: {organization_linkedin_url}")
@@ -330,8 +397,9 @@ async def enrich_organization_info_from_proxycurl(
             if standardized_url and not standardized_url.endswith('/'):
                 standardized_url += '/'
 
+        cache_key = _build_company_cache_key(standardized_url, profile_flags)
         # Check cache for standardized LinkedIn URL
-        cached_response = retrieve_output("enrich_organization_info_from_proxycurl", standardized_url)
+        cached_response = retrieve_output("enrich_organization_info_from_proxycurl", cache_key)
         if cached_response is not None:
             logger.info(f"Cache hit for organization LinkedIn URL: {standardized_url}")
             cached_response = transform_company_data(cached_response)
@@ -339,11 +407,7 @@ async def enrich_organization_info_from_proxycurl(
 
         # Fetch details using standardized LinkedIn URL
         url = 'https://enrichlayer.com/api/v2/company'
-        params = {
-            'url': standardized_url,
-            'use_cache': 'if-present',
-            'fallback_to_cache': 'on-error',
-        }
+        params = _build_company_profile_params(standardized_url, profile_flags)
         logger.debug(f"Making request to Proxycurl with params: {params}")
 
         async with aiohttp.ClientSession() as session:
@@ -353,7 +417,7 @@ 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", standardized_url, transformed_result)
+                        cache_output("enrich_organization_info_from_proxycurl", cache_key, transformed_result)
                         logger.info("Successfully retrieved and transformed organization info from Proxycurl by LinkedIn URL.")
                         return transformed_result
                     elif response.status == 429:
@@ -367,7 +431,7 @@ 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", standardized_url, {}
+                            "enrich_organization_info_from_proxycurl", cache_key, {}
                         )
                         return {}
                     else:
@@ -383,7 +447,8 @@ async def enrich_organization_info_from_proxycurl(
     # If organization domain is provided, resolve domain to LinkedIn URL and fetch data
     if organization_domain:
         logger.debug(f"Organization domain provided: {organization_domain}")
-        cached_response = retrieve_output("enrich_organization_info_from_proxycurl", organization_domain)
+        domain_cache_key = _build_company_cache_key(organization_domain, profile_flags)
+        cached_response = retrieve_output("enrich_organization_info_from_proxycurl", domain_cache_key)
         if cached_response is not None:
             logger.info(f"Cache hit for organization domain: {organization_domain}")
             return cached_response
@@ -414,12 +479,13 @@ async def enrich_organization_info_from_proxycurl(
 
                             profile_url = 'https://enrichlayer.com/api/v2/company'
                             try:
-                                async with session.get(profile_url, headers=HEADERS, params={'url': standardized_url}) as profile_response:
+                                profile_params = _build_company_profile_params(standardized_url, profile_flags)
+                                async with session.get(profile_url, headers=HEADERS, params=profile_params) as profile_response:
                                     logger.debug(f"Received profile response status: {profile_response.status}")
                                     if profile_response.status == 200:
                                         result = await profile_response.json()
                                         transformed_result = transform_company_data(result)
-                                        cache_output("enrich_organization_info_from_proxycurl", organization_domain, transformed_result)
+                                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, transformed_result)
                                         logger.info("Successfully retrieved and transformed organization info from Proxycurl by domain.")
                                         return transformed_result
                                     elif profile_response.status == 429:
@@ -445,7 +511,7 @@ 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", organization_domain, {})
+                        cache_output("enrich_organization_info_from_proxycurl", domain_cache_key, {})
                         return {}
                     else:
                         error_text = await response.text()

{dhisana-0.0.1.dev235 → dhisana-0.0.1.dev236}/src/dhisana.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dhisana
-Version: 0.0.1.dev235
+Version: 0.0.1.dev236
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin