leadgen-ai 1.2.0__tar.gz

leadgen_ai-1.2.0/.env.example

@@ -0,0 +1,30 @@
+# LeadGen AI — use ANY OpenAI-compatible API
+# Developed by Gyan Ranjan
+
+# --- Pick ONE key (whichever provider you use) ---
+OPENAI_API_KEY=
+# GROQ_API_KEY=
+# GEMINI_API_KEY=
+# DEEPSEEK_API_KEY=
+# OPENROUTER_API_KEY=
+# MISTRAL_API_KEY=
+# TOGETHER_API_KEY=
+# XAI_API_KEY=
+# LEADGEN_API_KEY=          # generic alias
+# API_KEY=                  # generic alias
+
+# --- Optional: force provider / model ---
+# LEADGEN_PROVIDER=openai
+# LEADGEN_MODEL=gpt-4o
+# Famous shortcuts: gpt-4o, gpt-4o-mini, gemini-2.0-flash, llama-3.3-70b,
+#                   deepseek-chat, mistral-large, claude-3.5-sonnet, o3-mini
+
+# --- Custom OpenAI-compatible endpoint (Ollama, vLLM, Azure, etc.) ---
+# LEADGEN_PROVIDER=custom
+# LEADGEN_BASE_URL=http://localhost:11434/v1
+# LEADGEN_MODEL=llama3.2
+# LEADGEN_API_KEY=ollama
+
+# LEADGEN_WEB_SEARCH=1
+# DEFAULT_LEAD_COUNT=10
+# MIN_LEAD_SCORE=40

leadgen_ai-1.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Gyan Ranjan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

leadgen_ai-1.2.0/MANIFEST.in

@@ -0,0 +1,14 @@
+include README.md
+include LICENSE
+include requirements.txt
+include .env.example
+include leadgen.cmd
+include run.ps1
+include run.bat
+include install.ps1
+recursive-include agent *.py
+prune output
+prune .venv
+global-exclude __pycache__
+global-exclude *.py[cod]
+global-exclude .env

leadgen_ai-1.2.0/PKG-INFO

@@ -0,0 +1,158 @@
+Metadata-Version: 2.4
+Name: leadgen-ai
+Version: 1.2.0
+Summary: Search any keywords and generate real sales leads. Works with any AI API (OpenAI, Groq, Gemini, DeepSeek, OpenRouter, …). Developed by Gyan Ranjan.
+Author: Gyan Ranjan
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/Gyan4589/leadgen-ai
+Project-URL: Repository, https://github.com/Gyan4589/leadgen-ai
+Project-URL: Issues, https://github.com/Gyan4589/leadgen-ai/issues
+Keywords: leads,sales,cli,ai,lead-generation,openai,gpt
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Office/Business
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=1.60.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: typer>=0.12.0
+Requires-Dist: ddgs>=9.0.0
+Dynamic: license-file
+
+# LeadGen AI
+
+**Search any keywords → get real sales leads**
+
+**Works with any AI API** — OpenAI, Groq, Gemini, DeepSeek, OpenRouter, Mistral, Together, custom OpenAI-compatible servers, and more.
+
+**Developed by Gyan Ranjan**
+
+---
+
+## Install
+
+```bash
+pip install leadgen-ai
+```
+
+From GitHub:
+
+```bash
+pip install git+https://github.com/Gyan4589/leadgen-ai.git
+```
+
+---
+
+## Setup (any API key)
+
+Create a `.env` or set an environment variable. **Use the key for the provider you choose:**
+
+```bash
+# OpenAI
+set OPENAI_API_KEY=sk-...
+
+# or Groq (fast + free tier)
+set GROQ_API_KEY=gsk_...
+
+# or Google Gemini
+set GEMINI_API_KEY=...
+
+# or DeepSeek / OpenRouter / Mistral
+set DEEPSEEK_API_KEY=...
+set OPENROUTER_API_KEY=...
+set MISTRAL_API_KEY=...
+
+# or generic
+set LEADGEN_API_KEY=...
+set LEADGEN_BASE_URL=https://api.openai.com/v1
+set LEADGEN_MODEL=gpt-4o
+```
+
+---
+
+## Usage
+
+```bash
+# list popular models
+leadgen models
+
+# search keywords
+leadgen search "dental clinics Mumbai" -n 8
+
+# pick a famous model
+leadgen search "real estate agents Texas" -m gpt-4o -n 5
+leadgen search "AI startups Bangalore" -m gemini-2.0-flash
+leadgen search "gyms Delhi" -p groq -m llama-3.3-70b
+leadgen search "HR SaaS USA" -m claude-3.5-sonnet   # via OpenRouter key
+
+# custom OpenAI-compatible endpoint (Ollama, vLLM, Azure proxy, etc.)
+leadgen search "cafes NYC" --provider custom --base-url http://localhost:11434/v1 --api-key ollama -m llama3.2
+
+# interactive
+leadgen
+```
+
+---
+
+## Popular models
+
+| Shortcut | Provider |
+|----------|----------|
+| `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `o3-mini` | OpenAI |
+| `gemini-2.0-flash`, `gemini-1.5-pro` | Google |
+| `llama-3.3-70b` | Groq |
+| `deepseek-chat` | DeepSeek |
+| `mistral-large` | Mistral |
+| `claude-3.5-sonnet`, `claude-sonnet-4` | OpenRouter |
+
+```bash
+leadgen models
+```
+
+---
+
+## How it works
+
+1. You type **keywords**  
+2. Live **web search** finds public company pages  
+3. Your chosen **LLM** scores leads + drafts outreach  
+4. Exports **CSV / JSON** to `output/`
+
+---
+
+## Flags
+
+| Flag | Meaning |
+|------|---------|
+| `-n / --count` | Max leads |
+| `-m / --model` | Model name or famous shortcut |
+| `-p / --provider` | openai, groq, gemini, deepseek, openrouter, mistral, custom |
+| `--base-url` | Custom API base URL |
+| `--api-key` | Pass key on CLI (prefer env for safety) |
+| `-g / --geo` | Geography filter |
+| `--min-score` | Drop weak leads |
+
+---
+
+## Ethics
+
+- Public sources only  
+- No invented private emails  
+- Verify before outreach  
+- Respect spam / privacy laws  
+
+---
+
+## Credits
+
+**LeadGen AI**  
+**Developed by Gyan Ranjan**  
+https://github.com/Gyan4589/leadgen-ai

leadgen_ai-1.2.0/README.md

@@ -0,0 +1,129 @@
+# LeadGen AI
+
+**Search any keywords → get real sales leads**
+
+**Works with any AI API** — OpenAI, Groq, Gemini, DeepSeek, OpenRouter, Mistral, Together, custom OpenAI-compatible servers, and more.
+
+**Developed by Gyan Ranjan**
+
+---
+
+## Install
+
+```bash
+pip install leadgen-ai
+```
+
+From GitHub:
+
+```bash
+pip install git+https://github.com/Gyan4589/leadgen-ai.git
+```
+
+---
+
+## Setup (any API key)
+
+Create a `.env` or set an environment variable. **Use the key for the provider you choose:**
+
+```bash
+# OpenAI
+set OPENAI_API_KEY=sk-...
+
+# or Groq (fast + free tier)
+set GROQ_API_KEY=gsk_...
+
+# or Google Gemini
+set GEMINI_API_KEY=...
+
+# or DeepSeek / OpenRouter / Mistral
+set DEEPSEEK_API_KEY=...
+set OPENROUTER_API_KEY=...
+set MISTRAL_API_KEY=...
+
+# or generic
+set LEADGEN_API_KEY=...
+set LEADGEN_BASE_URL=https://api.openai.com/v1
+set LEADGEN_MODEL=gpt-4o
+```
+
+---
+
+## Usage
+
+```bash
+# list popular models
+leadgen models
+
+# search keywords
+leadgen search "dental clinics Mumbai" -n 8
+
+# pick a famous model
+leadgen search "real estate agents Texas" -m gpt-4o -n 5
+leadgen search "AI startups Bangalore" -m gemini-2.0-flash
+leadgen search "gyms Delhi" -p groq -m llama-3.3-70b
+leadgen search "HR SaaS USA" -m claude-3.5-sonnet   # via OpenRouter key
+
+# custom OpenAI-compatible endpoint (Ollama, vLLM, Azure proxy, etc.)
+leadgen search "cafes NYC" --provider custom --base-url http://localhost:11434/v1 --api-key ollama -m llama3.2
+
+# interactive
+leadgen
+```
+
+---
+
+## Popular models
+
+| Shortcut | Provider |
+|----------|----------|
+| `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `o3-mini` | OpenAI |
+| `gemini-2.0-flash`, `gemini-1.5-pro` | Google |
+| `llama-3.3-70b` | Groq |
+| `deepseek-chat` | DeepSeek |
+| `mistral-large` | Mistral |
+| `claude-3.5-sonnet`, `claude-sonnet-4` | OpenRouter |
+
+```bash
+leadgen models
+```
+
+---
+
+## How it works
+
+1. You type **keywords**  
+2. Live **web search** finds public company pages  
+3. Your chosen **LLM** scores leads + drafts outreach  
+4. Exports **CSV / JSON** to `output/`
+
+---
+
+## Flags
+
+| Flag | Meaning |
+|------|---------|
+| `-n / --count` | Max leads |
+| `-m / --model` | Model name or famous shortcut |
+| `-p / --provider` | openai, groq, gemini, deepseek, openrouter, mistral, custom |
+| `--base-url` | Custom API base URL |
+| `--api-key` | Pass key on CLI (prefer env for safety) |
+| `-g / --geo` | Geography filter |
+| `--min-score` | Drop weak leads |
+
+---
+
+## Ethics
+
+- Public sources only  
+- No invented private emails  
+- Verify before outreach  
+- Respect spam / privacy laws  
+
+---
+
+## Credits
+
+**LeadGen AI**  
+**Developed by Gyan Ranjan**  
+https://github.com/Gyan4589/leadgen-ai

leadgen_ai-1.2.0/agent/__init__.py

@@ -0,0 +1,6 @@
+"""LeadGen AI — keyword lead search with any AI API. Developed by Gyan Ranjan."""
+
+from .pipeline import LeadAgent
+from .branding import APP_NAME, CREDIT, DEVELOPER, VERSION
+
+__all__ = ["LeadAgent", "APP_NAME", "CREDIT", "DEVELOPER", "VERSION"]

leadgen_ai-1.2.0/agent/branding.py

@@ -0,0 +1,15 @@
+"""Product branding — LeadGen AI by Gyan Ranjan."""
+
+APP_NAME = "LeadGen AI"
+APP_TAGLINE = "Search any keywords → get real sales leads (any AI API)"
+DEVELOPER = "Gyan Ranjan"
+CREDIT = f"Developed by {DEVELOPER}"
+VERSION = "1.2.0"
+
+
+def banner_lines() -> str:
+    return (
+        f"[bold cyan]{APP_NAME}[/]  v{VERSION}\n"
+        f"[dim]{APP_TAGLINE}[/]\n"
+        f"[magenta]{CREDIT}[/]"
+    )

leadgen_ai-1.2.0/agent/config.py

@@ -0,0 +1,133 @@
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+from pathlib import Path
+
+from dotenv import load_dotenv
+
+from .models_catalog import FAMOUS_MODELS, PROVIDERS
+
+_ROOT = Path(__file__).resolve().parent.parent
+load_dotenv(_ROOT / ".env")
+load_dotenv()
+
+
+def _first_env(*names: str) -> str:
+    for name in names:
+        val = os.getenv(name, "").strip()
+        if val:
+            return val
+    return ""
+
+
+def resolve_api_key(provider: str) -> str:
+    """Accept any common API key env var so users can plug any provider."""
+    meta = PROVIDERS.get(provider, PROVIDERS["custom"])
+    # provider-specific first, then generic aliases
+    return _first_env(
+        meta["key_env"],
+        "LEADGEN_API_KEY",
+        "API_KEY",
+        "OPENAI_API_KEY",
+        "XAI_API_KEY",
+        "GROQ_API_KEY",
+        "ANTHROPIC_API_KEY",
+        "GEMINI_API_KEY",
+        "GOOGLE_API_KEY",
+        "DEEPSEEK_API_KEY",
+        "OPENROUTER_API_KEY",
+        "TOGETHER_API_KEY",
+        "MISTRAL_API_KEY",
+    )
+
+
+@dataclass(frozen=True)
+class Settings:
+    api_key: str
+    base_url: str
+    model: str
+    provider: str = "openai"
+    default_lead_count: int = 10
+    min_score: int = 50
+    use_web_search: bool = True
+
+    @classmethod
+    def from_env(
+        cls,
+        *,
+        provider: str | None = None,
+        model: str | None = None,
+        base_url: str | None = None,
+        api_key: str | None = None,
+    ) -> "Settings":
+        # CLI / env overrides
+        model_name = (model or os.getenv("LEADGEN_MODEL") or os.getenv("MODEL") or "").strip()
+        provider_name = (provider or os.getenv("LEADGEN_PROVIDER") or os.getenv("PROVIDER") or "").strip().lower()
+
+        # Resolve famous model shortcuts → provider + model id
+        if model_name and model_name.lower() in FAMOUS_MODELS:
+            auto_provider, auto_model = FAMOUS_MODELS[model_name.lower()]
+            if not provider_name:
+                provider_name = auto_provider
+            model_name = auto_model
+
+        if not provider_name:
+            # Auto-detect from which key is set
+            for p, meta in PROVIDERS.items():
+                if p == "custom":
+                    continue
+                if os.getenv(meta["key_env"], "").strip():
+                    provider_name = p
+                    break
+            if not provider_name:
+                provider_name = "openai"
+
+        if provider_name not in PROVIDERS:
+            provider_name = "custom"
+
+        meta = PROVIDERS[provider_name]
+        resolved_base = (
+            (base_url or "").strip()
+            or os.getenv("LEADGEN_BASE_URL", "").strip()
+            or os.getenv("OPENAI_BASE_URL", "").strip()
+            or meta["base_url"]
+        )
+        if not resolved_base:
+            resolved_base = "https://api.openai.com/v1"
+
+        if not model_name:
+            model_name = (
+                os.getenv("LEADGEN_MODEL", "").strip()
+                or meta["default_model"]
+            )
+
+        key = (api_key or "").strip() or resolve_api_key(provider_name)
+        if not key:
+            raise RuntimeError(
+                "Missing API key. Set any of these in .env or environment:\n"
+                "  OPENAI_API_KEY, GROQ_API_KEY, GEMINI_API_KEY, DEEPSEEK_API_KEY,\n"
+                "  OPENROUTER_API_KEY, MISTRAL_API_KEY, XAI_API_KEY, LEADGEN_API_KEY, API_KEY\n\n"
+                "Examples:\n"
+                "  set OPENAI_API_KEY=sk-...\n"
+                "  leadgen search \"dental clinics Mumbai\" --model gpt-4o\n"
+                "  leadgen search \"gyms Delhi\" --provider groq --model llama-3.3-70b\n"
+                "  leadgen models   # list popular models\n"
+            )
+
+        web = os.getenv("LEADGEN_WEB_SEARCH", "1").strip().lower() not in {
+            "0",
+            "false",
+            "no",
+            "off",
+        }
+
+        return cls(
+            api_key=key,
+            base_url=resolved_base.rstrip("/"),
+            model=model_name,
+            provider=provider_name,
+            default_lead_count=int(os.getenv("DEFAULT_LEAD_COUNT", "10")),
+            min_score=int(os.getenv("MIN_LEAD_SCORE", "50")),
+            use_web_search=web,
+        )

leadgen_ai-1.2.0/agent/export.py

@@ -0,0 +1,148 @@
+from __future__ import annotations
+
+import csv
+import json
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Iterable
+
+from .models import Lead, LeadRunResult
+
+CSV_FIELDS = [
+    "company_name",
+    "website",
+    "industry",
+    "company_size",
+    "location",
+    "description",
+    "contact_name",
+    "contact_title",
+    "contact_email",
+    "linkedin_url",
+    "source_url",
+    "buying_signals",
+    "fit_score",
+    "fit_reason",
+    "outreach_subject",
+    "outreach_email",
+    "next_action",
+]
+
+
+def default_output_dir() -> Path:
+    root = Path(__file__).resolve().parent.parent / "output"
+    root.mkdir(parents=True, exist_ok=True)
+    return root
+
+
+def stamp() -> str:
+    return datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
+
+
+def _lead_to_row(lead: Lead) -> dict:
+    row = lead.model_dump()
+    signals = row.get("buying_signals") or []
+    if isinstance(signals, list):
+        row["buying_signals"] = "; ".join(str(s) for s in signals)
+    return row
+
+
+def export_csv(leads: list[Lead], path: Path) -> Path:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=CSV_FIELDS, extrasaction="ignore")
+        writer.writeheader()
+        for lead in leads:
+            writer.writerow(_lead_to_row(lead))
+    return path
+
+
+def export_json(result: LeadRunResult, path: Path) -> Path:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(result.model_dump_json(indent=2), encoding="utf-8")
+    return path
+
+
+def _normalize_key(name: str, website: str | None = None) -> str:
+    base = (name or "").strip().lower()
+    site = (website or "").strip().lower().removeprefix("https://").removeprefix("http://").removeprefix("www.")
+    site = site.rstrip("/")
+    return f"{base}|{site}"
+
+
+def load_csv_rows(path: Path) -> list[dict]:
+    if not path.is_file():
+        return []
+    with path.open(newline="", encoding="utf-8") as f:
+        return list(csv.DictReader(f))
+
+
+def merge_lead_rows(rows: Iterable[dict]) -> list[dict]:
+    """Dedupe by company+website, keep highest fit_score."""
+    best: dict[str, dict] = {}
+    for row in rows:
+        name = (row.get("company_name") or "").strip()
+        if not name:
+            continue
+        key = _normalize_key(name, row.get("website"))
+        try:
+            score = int(float(row.get("fit_score") or 0))
+        except (TypeError, ValueError):
+            score = 0
+        row = {**row, "fit_score": score}
+        prev = best.get(key)
+        if prev is None:
+            best[key] = row
+            continue
+        try:
+            prev_score = int(float(prev.get("fit_score") or 0))
+        except (TypeError, ValueError):
+            prev_score = 0
+        if score >= prev_score:
+            best[key] = row
+    merged = list(best.values())
+    merged.sort(key=lambda r: int(r.get("fit_score") or 0), reverse=True)
+    return merged
+
+
+def write_rows_csv(rows: list[dict], path: Path) -> Path:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=CSV_FIELDS, extrasaction="ignore")
+        writer.writeheader()
+        for row in rows:
+            out = {k: row.get(k, "") for k in CSV_FIELDS}
+            writer.writerow(out)
+    return path
+
+
+def merge_all_csvs(out_dir: Path | None = None) -> Path:
+    """Merge every leads_*.csv in output/ into all_leads.csv (deduped)."""
+    out = out_dir or default_output_dir()
+    rows: list[dict] = []
+    for path in sorted(out.glob("leads_*.csv")):
+        rows.extend(load_csv_rows(path))
+    # Also include existing master if present
+    master = out / "all_leads.csv"
+    if master.is_file():
+        rows.extend(load_csv_rows(master))
+    merged = merge_lead_rows(rows)
+    return write_rows_csv(merged, master)
+
+
+def append_to_master(leads: list[Lead], out_dir: Path | None = None) -> Path:
+    out = out_dir or default_output_dir()
+    master = out / "all_leads.csv"
+    existing = load_csv_rows(master)
+    new_rows = [_lead_to_row(lead) for lead in leads]
+    merged = merge_lead_rows(existing + new_rows)
+    return write_rows_csv(merged, master)
+
+
+def export_all(result: LeadRunResult, out_dir: Path | None = None) -> dict[str, Path]:
+    out = out_dir or default_output_dir()
+    ts = stamp()
+    csv_path = export_csv(result.leads, out / f"leads_{ts}.csv")
+    json_path = export_json(result, out / f"leads_{ts}.json")
+    master_path = append_to_master(result.leads, out)
+    return {"csv": csv_path, "json": json_path, "all": master_path}