dhisana 0.0.1.dev86__tar.gz → 0.0.1.dev231__tar.gz

{dhisana-0.0.1.dev86 → dhisana-0.0.1.dev231}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: dhisana
-Version: 0.0.1.dev86
+Version: 0.0.1.dev231
 Summary: A Python SDK for Dhisana AI Platform
 Home-page: https://github.com/dhisana-ai/dhisana-python-sdk
 Author: Admin
@@ -30,6 +30,9 @@ Requires-Dist: hubspot-api-client
 Requires-Dist: tldextract
 Requires-Dist: pyperclip
 Requires-Dist: azure-storage-blob
+Requires-Dist: email_validator
+Requires-Dist: fqdn
+Requires-Dist: json_repair
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

dhisana-0.0.1.dev231/README.md

@@ -0,0 +1,257 @@
+# Dhisana Python SDK
+
+A Python SDK for interacting with Dhisana AI services.
+
+## Installation
+
+```bash
+pip install dhisana
+```
+
+## Usage
+
+```python
+from dhisana.utils.agent_tools import (
+    search_google_maps,
+    enrich_people_with_apollo,
+    search_google,
+    search_google_jobs,
+    search_google_news,
+    get_html_content_from_url,
+    parse_html_content,
+    extract_image_links,
+    extract_head_section_from_html_content,
+    get_email_if_exists,
+    search_crunchbase,
+    search_people_with_apollo,
+    search_companies_with_apollo,
+    enrich_company_with_apollo,
+    get_job_postings_from_apollo
+)
+# Your code here
+```
+
+## Steps to Create and Publish the Package
+
+### Ensure you have the latest versions of setuptools and wheel
+
+```bash
+pip install --upgrade setuptools wheel
+```
+
+### Build the Package
+
+```bash
+pip install .
+```
+
+### Upload to PyPI
+
+First, install twine:
+
+```bash
+pip install --upgrade build twine
+python -m build
+pip install twine
+```
+
+### Then upload your package (you'll need a PyPI account)
+
+```bash
+twine upload dist/\*
+```
+
+### Install the Package Locally for Testing
+
+You can install the package locally to test it before uploading:
+
+```bash
+pip install -e .
+```
+
+The -e flag installs the package in editable mode, which is useful during development.
+
+## Run Tests
+
+```bash
+pip install pytest
+pytest tests/
+```
+
+### Using the Package in Other Projects
+
+Once your package is published to PyPI, other users can install it using:
+
+```bash
+pip install dhisana
+```
+
+They can then import your SDK as:
+
+```bash
+from dhisana.utils.agent_tools import (
+    search_google_maps,
+    enrich_people_with_apollo,
+    search_google,
+    search_google_jobs,
+    search_google_news,
+    get_html_content_from_url,
+    parse_html_content,
+    extract_image_links,
+    extract_head_section_from_html_content,
+    get_email_if_exists,
+    search_crunchbase,
+    search_people_with_apollo,
+    search_companies_with_apollo,
+    enrich_company_with_apollo,
+    get_job_postings_from_apollo
+)
+
+# Use the functionalities provided by your SDK
+```
+
+### To use locally
+
+```bash
+pip install -e /path/to/other/project
+```
+
+### To use CLI
+
+You can use the CLI provided by the Dhisana AI SDK. To see the available commands and options, use:
+
+```bash
+dhisana --help
+```
+
+This will display:
+
+```bash
+Usage: dhisana [OPTIONS] COMMAND [ARGS]...
+
+    Dhisana AI SDK CLI.
+
+Options:
+    --help  Show this message and exit.
+
+Commands:
+    dataset-cli     Commands for managing datasets.
+    model-cli       Commands for managing models.
+    prediction-cli  Commands for running predictions.
+```
+
+## Proxycurl Job Leads Example
+
+Set `PROXY_CURL_API_KEY` in your environment before running functions that call Proxycurl.
+
+```bash
+export PROXY_CURL_API_KEY=your_api_key
+```
+
+Example usage to search for SDR roles and retrieve hiring manager leads:
+
+```python
+import asyncio
+from dhisana.utils.proxy_curl_tools import find_leads_by_job_openings_proxy_curl
+
+async def main():
+    leads = await find_leads_by_job_openings_proxy_curl(
+        {"job_title": "SDR", "location": "United States"},
+        hiring_manager_roles=["VP of Sales", "Head of Sales"],
+    )
+    print(leads)
+
+asyncio.run(main())
+```
+
+## Proxycurl Job Search Example
+
+Use `proxycurl_job_search` to list jobs posted by a company. Parameters mirror
+Proxycurl's job search endpoint.
+
+### Parameters
+
+- `job_type` – one of `full-time`, `part-time`, `contract`, `internship`,
+  `temporary`, `volunteer`, or `anything`.
+- `experience_level` – `internship`, `entry_level`, `associate`,
+  `mid_senior_level`, `director`, or `anything`.
+- `when` – posted time such as `yesterday`, `past-week`, `past-month`, or
+  `anytime`.
+- `flexibility` – `remote`, `on-site`, `hybrid`, or `anything`.
+- `geo_id` – location identifier, e.g. `92000000` for worldwide.
+- `keyword` – keyword to match in the job title.
+- `search_id` – company search identifier from the Company Profile API.
+
+Example usage:
+
+```python
+import asyncio
+from dhisana.utils.proxycurl_search_leads import JobSearchParams, proxycurl_job_search
+
+async def main():
+    jobs = await proxycurl_job_search(
+        JobSearchParams(
+            search_id="2790400",
+            keyword="engineer",
+            job_type="full-time",
+            experience_level="mid_senior_level",
+            when="past-month",
+            flexibility="remote",
+            geo_id=92000000,
+        ),
+        max_entries=2,
+    )
+    print(jobs)
+
+asyncio.run(main())
+```
+
+## Proxycurl Get Company Search ID Example
+
+Use `proxycurl_get_company_search_id` to retrieve a company's search ID, which is required for other Proxycurl operations like job searches. This function calls Proxycurl's Company Profile endpoint.
+
+### Function Parameters
+
+- `company_url` – LinkedIn company profile URL (e.g., `https://www.linkedin.com/company/microsoft/`)
+- `tool_config` – Optional tool configuration containing API key
+
+### Return Value
+
+Returns a dictionary with:
+
+- `search_id` – The company's search ID (required for job operations)
+- `name` – Company name
+- `linkedin_internal_id` – LinkedIn's internal company ID
+- `industry` – Company industry
+- `company_url` – The original URL provided
+- `error` – Error message (if any errors occurred)
+
+Example usage:
+
+```python
+import asyncio
+from dhisana.utils.proxycurl_search_leads import (
+    proxycurl_get_company_search_id,
+    proxycurl_job_count,
+    JobSearchParams
+)
+
+async def main():
+    # Get company search ID
+    company_result = await proxycurl_get_company_search_id(
+        "https://www.linkedin.com/company/microsoft/"
+    )
+
+    if company_result.get("search_id"):
+        print(f"Company: {company_result['name']}")
+        print(f"Search ID: {company_result['search_id']}")
+
+        # Use the search ID for job operations
+        job_params = JobSearchParams(search_id=company_result["search_id"])
+        job_count = await proxycurl_job_count(job_params)
+        print(f"Total jobs: {job_count.get('count', 0)}")
+    else:
+        print(f"Error: {company_result.get('error')}")
+
+asyncio.run(main())
+```

{dhisana-0.0.1.dev86 → dhisana-0.0.1.dev231}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='dhisana',  
-    version='0.0.1-dev86',
+    version='0.0.1-dev231',
     description='A Python SDK for Dhisana AI Platform',
     author='Admin',
     author_email='contact@dhisana.ai',
@@ -29,7 +29,10 @@ setup(
         'hubspot-api-client',
         'tldextract',
         'pyperclip',
-        'azure-storage-blob'
+        'azure-storage-blob',
+        'email_validator',
+        'fqdn',
+        'json_repair'
     ],
     entry_points={
         'console_scripts': [

{dhisana-0.0.1.dev86 → dhisana-0.0.1.dev231}/src/dhisana/schemas/common.py

@@ -363,3 +363,35 @@ class Integration(IntegrationBase):
 
 Integration.model_rebuild()
 IntegrationUpdate.model_rebuild()
+
+class BodyFormat(str, Enum):
+    AUTO = "auto"
+    HTML = "html"
+    TEXT = "text"
+
+
+class SendEmailContext(BaseModel):
+    recipient: str
+    subject: str
+    body: str
+    sender_name: str
+    sender_email: str
+    labels: Optional[List[str]]
+    body_format: BodyFormat = BodyFormat.AUTO
+    
+class QueryEmailContext(BaseModel):
+    start_time: str
+    end_time: str
+    sender_email: str
+    unread_only: bool = True
+    labels: Optional[List[str]] = None
+    
+
+class ReplyEmailContext(BaseModel):
+    message_id: str
+    reply_body: str
+    sender_email: str
+    sender_name: str
+    mark_as_read: str = "True"
+    add_labels: Optional[List[str]] = None
+    reply_body_format: BodyFormat = BodyFormat.AUTO

{dhisana-0.0.1.dev86 → dhisana-0.0.1.dev231}/src/dhisana/schemas/sales.py

@@ -1,24 +1,31 @@
+import json
+
 from uuid import UUID
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator
 from typing import List, Optional, Dict, Any
 from enum import Enum
 from typing import Optional, List, Dict, Literal
 
-from dhisana.schemas.common import User
 
 # -----------------------------
 # Lead-List-Specific Schemas
 # -----------------------------
 
 class Lead(BaseModel):
-    id: Optional[str] = None
+    id: Optional[UUID] = None
     full_name: Optional[str] = None
     first_name: Optional[str] = None
     last_name: Optional[str] = None
     email: Optional[str] = None
     user_linkedin_url: Optional[str] = None
     user_linkedin_salesnav_url: Optional[str] = None
+    organization_linkedin_url: Optional[str] = None
+    organization_linkedin_salesnav_url: Optional[str] = None
+    linkedin_follower_count: Optional[int] = None
     primary_domain_of_organization: Optional[str] = None
+    twitter_handle: Optional[str] = None
+    twitch_handle: Optional[str] = None
+    github_handle: Optional[str] = None
     job_title: Optional[str] = None
     phone: Optional[str] = None
     headline: Optional[str] = None
@@ -26,25 +33,69 @@ class Lead(BaseModel):
     organization_name: Optional[str] = None
     organization_website: Optional[str] = None
     summary_about_lead: Optional[str] = None
+
+    qualification_score: Optional[float] = None
+    qualification_reason: Optional[str] = None
+    revenue: Optional[str] = None
+    company_size: Optional[str] = None
+    industry: Optional[str] = None
+
+    keywords: Optional[Any] = None
+    tags: List[str] = []
+    notes: List[str] = []
+    additional_properties: Optional[Dict[str, Any]] = {}
     workflow_stage: Optional[str] = None
-    assigned_to: Optional[str] = None
-    engaged: Optional[bool] = None
+
+    engaged: bool = False
     last_contact: Optional[int] = None
-    additional_properties: Optional[Dict[str, str]] = None
     research_summary: Optional[str] = None
     task_ids: Optional[List[str]] = None
-    email_validation_status: Optional[
-        Literal["not_started", "in_progress", "valid", "invalid"]
-    ] = None
-    linkedin_validation_status: Optional[
-        Literal["not_started", "in_progress", "valid", "invalid"]
-    ] = None
-    research_status: Optional[
-        Literal["not_started", "in_progress", "done", "failed"]
-    ] = None
-    enchrichment_status: Optional[
-        Literal["not_started", "in_progress", "done", "failed"]
-    ] = None
+    email_validation_status: Optional[str] = None
+    linkedin_validation_status: Optional[str] = None
+    research_status: Optional[str] = None
+    enchrichment_status: Optional[str] = None
+
+
+    @field_validator("linkedin_follower_count", mode="before")
+    @classmethod
+    def parse_linkedin_follower_count(cls, v):
+        if v is None or v == "":
+            return None
+        if isinstance(v, str):
+            v = v.strip()
+            if v == "":
+                return None
+            try:
+                return int(v)
+            except ValueError:
+                raise ValueError("linkedin_follower_count must be an integer")
+        return v
+
+    @field_validator("notes", mode="before")
+    @classmethod
+    def ensure_notes_list(cls, v):
+        """Coerce notes to a list of strings.
+        Handles legacy cases where the DB may contain a scalar or JSON string.
+        """
+        if v is None:
+            return []
+        if isinstance(v, list):
+            # Ensure all elements are strings
+            return [str(item) if not isinstance(item, str) else item for item in v]
+        if isinstance(v, str):
+            # Try to parse JSON array; if not, wrap as single-note list
+            try:
+                parsed = json.loads(v)
+                if isinstance(parsed, list):
+                    return [str(item) if not isinstance(item, str) else item for item in parsed]
+            except Exception:
+                pass
+            return [v]
+        # Fallback: wrap any other scalar/object as a single string entry
+        try:
+            return [json.dumps(v)]
+        except Exception:
+            return [str(v)]
 
 
 class LeadList(BaseModel):
@@ -243,6 +294,7 @@ class MessageGenerationInstructions(BaseModel):
     """
     instructions_to_generate_message: Optional[str] = None
     prompt_engineering_guidance: Optional[PromptEngineeringGuidance] = None
+    use_cache: Optional[bool] = True
 
 class CampaignContext(BaseModel):
     """
@@ -272,6 +324,10 @@ class MessageItem(BaseModel):
         ...,
         description="Unique identifier for the message"
     )
+    thread_id: str = Field(
+        ...,
+        description="Unique identifier for the conversation thread"
+    )
     sender_name: str = Field(
         ...,
         description="Sender's display name (if available)"
@@ -300,6 +356,7 @@ class MessageItem(BaseModel):
         ...,
         description="Body of the message in plain text"
     )
+    html_body: Optional[str] = None
 
 class MessageResponse(BaseModel):
     """
@@ -435,14 +492,14 @@ class HubSpotLeadInformation(BaseModel):
     organization_name: str = Field("", description="Current Company where lead works")
     organization_website: str = Field("", description="Current Company website of the lead")
     organization_linkedin_url : str = Field("", description="Company LinkedIn URL")
-    additional_properties: Optional[Dict[str, str]] = None
+    additional_properties: Optional[Dict[str, Any]] = None
 
 class HubSpotCompanyinformation(BaseModel):
     primary_domain_of_organization: str = Field("", description="Primary domain of the organization")
     organization_name: str = Field("", description="Current Company where lead works")
     organization_website: str = Field("", description="Current Company website of the lead")
     organization_linkedin_url : str = Field("", description="Company LinkedIn URL")
-    additional_properties: Optional[Dict[str, str]] = None
+    additional_properties: Optional[Dict[str, Any]] = None
 
 
 # --------------------------------------------------------------------
@@ -459,6 +516,7 @@ HUBSPOT_TO_LEAD_MAPPING = {
     "address": "lead_location",         # You can choose "city", "state", etc. if you prefer
     "city": "lead_location",
     "domain": "primary_domain_of_organization",
+    "hs_linkedin_url": "user_linkedin_url",
 }
 
 class SmartListStatus(str, Enum):
@@ -478,6 +536,12 @@ class SmartListSourceType(str, Enum):
     CSV = "CSV"
     GOOGLE_SHEETS = "GOOGLE_SHEETS"
     CUSTOM_WEBSITE = "CUSTOM_WEBSITE"
+    GITHUB = "GITHUB"
+    ICP_SEARCH = "ICP_SEARCH"
+    LOCAL_BUSINESS = "LOCAL_BUSINESS"
+    GOOGLE_JOBS = "GOOGLE_JOBS"
+    WEBHOOK = "WEBHOOK"
+    GOOGLE_CUSTOM_SITE_SEARCH = "GOOGLE_CUSTOM_SITE_SEARCH"
 
 class SourceConfiguration(BaseModel):
     """
@@ -494,6 +558,15 @@ class SourceConfiguration(BaseModel):
     file_path: Optional[str] = None
     # For Google Sheets
     source_url: Optional[str] = None
+    # For Github
+    github_search_query: Optional[str] = None
+    github_max_repos: Optional[int] = None
+    github_max_contributors: Optional[int] = None
+    
+    # Custom website inputs 
+    custom_instructions_for_doing_pagination: Optional[str] = None
+    custom_instructions_for_data_extraction_from_page: Optional[str] = None
+    custom_instruction_to_fetch_details_page: Optional[str] = None
 
 class SmartListSource(BaseModel):
     """
@@ -555,6 +628,8 @@ class SmartListLead(BaseModel):
     organization_linkedin_url: Optional[str] = None
     organization_linkedin_salesnav_url: Optional[str] = None
     primary_domain_of_organization: Optional[str] = None
+    twitter_handle: Optional[str] = None
+    github_handle: Optional[str] = None
     job_title: Optional[str] = None
     phone: Optional[str] = None
     headline: Optional[str] = None
@@ -562,13 +637,18 @@ class SmartListLead(BaseModel):
     organization_name: Optional[str] = None
     organization_website: Optional[str] = None
     summary_about_lead: Optional[str] = None
-    keywords: Optional[List[str]] = None
-    additional_properties: Optional[Dict[str, str]] = None
+    keywords: Optional[Any] = None
+    additional_properties: Optional[Dict[str, Any]] = None
     research_summary: Optional[str] = None
 
     qualification_score: Optional[float] = None
     qualification_reason: Optional[str] = None
     source: Optional[str] = None
+    
+    email_validation_status: Optional[str] = None
+    linkedin_validation_status: Optional[str] = None
+    research_status: Optional[str] = None
+    enchrichment_status: Optional[str] = None
 
     agent_instance_id: Optional[UUID] = None
     organization_id: Optional[UUID] = None
@@ -576,7 +656,10 @@ class SmartListLead(BaseModel):
     created_at: Optional[int] = None
     updated_by: Optional[UUID] = None
     updated_at: Optional[int] = None
-
+    
+    revenue: Optional[str] = None
+    company_size: Optional[str] = None
+    industry: Optional[str] = None
     class Config:
         from_attributes = True
 
@@ -741,3 +824,118 @@ class LeadsQueryFilters(BaseModel):
         description="Ranges for organization number of employees."
     )
 
+
+class CompanyQueryFilters(BaseModel):
+    """
+    Defines the filter parameters for querying companies/organizations in the Apollo database.
+    All fields are optional and default to None if not specified by user.
+    """
+
+    # Core company search parameters
+    organization_locations: Optional[List[str]] = Field(
+        default=None,
+        description="List of organization headquarters locations (city, state, country)."
+    )
+
+    organization_num_employees_ranges: Optional[List[str]] = Field(
+        default=None,
+        description="Employee count ranges, e.g. ['1,10', '11,50', '51,200']. Use specific ranges."
+    )
+
+    min_employees: Optional[int] = Field(
+        default=None,
+        description="Minimum number of employees (>=1). Internally converted to a numeric range."
+    )
+    
+    max_employees: Optional[int] = Field(
+        default=None,
+        description="Maximum number of employees (<=100000). Internally converted to a numeric range."
+    )
+
+    organization_industries: Optional[List[str]] = Field(
+        default=None,
+        description="List of organization industries."
+    )
+
+    organization_industry_tag_ids: Optional[List[str]] = Field(
+        default=None,
+        description="List of industry tag IDs, e.g. ['5567cd4773696439b10b0000']."
+    )
+
+    # Revenue filters
+    revenue_range_min: Optional[int] = Field(
+        default=None,
+        description="Minimum company revenue in USD."
+    )
+    
+    revenue_range_max: Optional[int] = Field(
+        default=None,
+        description="Maximum company revenue in USD."
+    )
+
+    # Funding and growth
+    organization_latest_funding_stage_cd: Optional[List[str]] = Field(
+        default=None,
+        description="List of funding stage codes, e.g. ['2', '3', '10']."
+    )
+
+    # Technology and keywords
+    currently_using_any_of_technology_uids: Optional[List[str]] = Field(
+        default=None,
+        description="Technology UIDs used by the organization, e.g. ['google_font_api']."
+    )
+
+    q_keywords: Optional[str] = Field(
+        default=None,
+        description="Keywords to search for in company descriptions, names, etc."
+    )
+
+    q_organization_domains: Optional[List[str]] = Field(
+        default=None,
+        description="Specific company domains to search for, e.g. ['microsoft.com', 'google.com']."
+    )
+
+    # Company-specific filters
+    organization_ids: Optional[List[str]] = Field(
+        default=None,
+        description="Specific Apollo organization IDs to include."
+    )
+
+    not_organization_ids: Optional[List[str]] = Field(
+        default=None,
+        description="Apollo organization IDs to exclude from results."
+    )
+
+    # Search lists
+    q_organization_search_list_id: Optional[str] = Field(
+        default=None,
+        description="Include only organizations in a specific search list."
+    )
+    
+    q_not_organization_search_list_id: Optional[str] = Field(
+        default=None,
+        description="Exclude organizations in a specific search list."
+    )
+
+    # Sorting
+    sort_by_field: Optional[str] = Field(
+        default=None,
+        description="Sort field, e.g. 'name', 'employee_count', 'last_updated', etc."
+    )
+    
+    sort_ascending: Optional[bool] = Field(
+        default=None,
+        description="Sort ascending (True) or descending (False)."
+    )
+
+    # Additional filters that might be useful
+    organization_founded_year_min: Optional[int] = Field(
+        default=None,
+        description="Minimum founding year for the organization."
+    )
+    
+    organization_founded_year_max: Optional[int] = Field(
+        default=None,
+        description="Maximum founding year for the organization."
+    )
+