webscout 8.2.6__py3-none-any.whl → 8.2.8__py3-none-any.whl

{webscout-8.2.6.dist-info → webscout-8.2.8.dist-info}/METADATA

@@ -1,9 +1,8 @@
 Metadata-Version: 2.4
 Name: webscout
-Version: 8.2.6
+Version: 8.2.8
 Summary: Search for anything using Google, DuckDuckGo, phind.com, Contains AI models, can transcribe yt videos, temporary email and phone number generation, has TTS support, webai (terminal gpt and open interpreter) and offline LLMs and more
-Author: OEvortex
-Author-email: helpingai5@gmail.com
+Author-email: OEvortex <helpingai5@gmail.com>
 License: HelpingAI
 Project-URL: Source, https://github.com/OE-LUCIFER/Webscout
 Project-URL: Tracker, https://github.com/OE-LUCIFER/Webscout/issues
@@ -40,7 +39,6 @@ Requires-Dist: wheel
 Requires-Dist: pip
 Requires-Dist: nodriver
 Requires-Dist: mistune
-Requires-Dist: tenacity
 Requires-Dist: curl_cffi
 Requires-Dist: nest-asyncio
 Requires-Dist: websocket-client
@@ -50,7 +48,6 @@ Requires-Dist: markdownify
 Requires-Dist: requests
 Requires-Dist: google-generativeai
 Requires-Dist: lxml>=5.2.2
-Requires-Dist: termcolor
 Requires-Dist: orjson
 Requires-Dist: PyYAML
 Requires-Dist: ollama
@@ -60,27 +57,18 @@ Requires-Dist: cloudscraper
 Requires-Dist: html5lib
 Requires-Dist: aiofiles
 Requires-Dist: openai
-Requires-Dist: prompt-toolkit
-Requires-Dist: pyreqwest_impersonate
 Requires-Dist: gradio_client
 Requires-Dist: psutil
 Requires-Dist: aiohttp
 Provides-Extra: dev
 Requires-Dist: ruff>=0.1.6; extra == "dev"
 Requires-Dist: pytest>=7.4.2; extra == "dev"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: keywords
-Dynamic: license
+Provides-Extra: api
+Requires-Dist: fastapi; extra == "api"
+Requires-Dist: uvicorn[standard]; extra == "api"
+Requires-Dist: pydantic; extra == "api"
+Requires-Dist: python-multipart; extra == "api"
 Dynamic: license-file
-Dynamic: project-url
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 <div align="center">
   <a href="https://github.com/OEvortex/Webscout">
@@ -101,6 +89,7 @@ Dynamic: summary
     <a href="https://pepy.tech/project/webscout"><img src="https://static.pepy.tech/badge/webscout/month?style=flat-square" alt="Monthly Downloads"></a>
     <a href="https://pepy.tech/project/webscout"><img src="https://static.pepy.tech/badge/webscout?style=flat-square" alt="Total Downloads"></a>
     <a href="#"><img src="https://img.shields.io/pypi/pyversions/webscout?style=flat-square&logo=python" alt="Python Version"></a>
+    <a href="https://deepwiki.com/OEvortex/Webscout"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
   </p>
 </div>
 
@@ -111,6 +100,7 @@ Dynamic: summary
 - [🌟 Key Features](#-features)
 - [⚙️ Installation](#️-installation)
 - [🖥️ Command Line Interface](#️-command-line-interface)
+- [🔄 OpenAI-Compatible API Server](#-openai-compatible-api-server)
 - [🔍 Search Engines](#-search-engines)
 - [🦆 DuckDuckGo Search](#-duckduckgo-search-with-webs-and-asyncwebs)
 - [💻 WEBS API Reference](#-webs-api-reference)
@@ -128,7 +118,7 @@ Dynamic: summary
 > - **OpenAI Compatibility:** Use providers with OpenAI-compatible interfaces
 > - **Local LLM Compatibility:** Run local models with [Inferno](https://github.com/HelpingAI/inferno), an OpenAI-compatible server (now a standalone package)
 >
-> Choose the approach that best fits your needs! For OpenAI compatibility, check the [OpenAI Providers README](webscout/Provider/OPENAI/README.md).
+> Choose the approach that best fits your needs! For OpenAI compatibility, check the [OpenAI Providers README](webscout/Provider/OPENAI/README.md) or see the [OpenAI-Compatible API Server](#-openai-compatible-api-server) section below.
 
 > [!NOTE]
 > Webscout supports over 90 AI providers including: LLAMA, C4ai, Venice, Copilot, HuggingFaceChat, PerplexityLabs, DeepSeek, WiseCat, GROQ, OPENAI, GEMINI, DeepInfra, Meta, YEPCHAT, TypeGPT, ChatGPTClone, ExaAI, Claude, Anthropic, Cloudflare, AI21, Cerebras, and many more. All providers follow similar usage patterns with consistent interfaces.
@@ -225,7 +215,6 @@ python -m webscout --help
 | Command | Description |
 |---------|-------------|
 | `python -m webscout answers -k "query"` | Perform an answers search |
-| `python -m webscout chat` | Start an interactive AI chat session |
 | `python -m webscout images -k "query"` | Search for images |
 | `python -m webscout maps -k "query"` | Perform a maps search |
 | `python -m webscout news -k "query"` | Search for news articles |
@@ -282,6 +271,111 @@ For more information, visit the [Inferno GitHub repository](https://github.com/H
 > - 32 GB of RAM for 33B models
 > - GPU acceleration is recommended for better performance
 
+<details open>
+<summary><b>🔄 OpenAI-Compatible API Server</b></summary>
+<p>
+
+Webscout includes an OpenAI-compatible API server that allows you to use any supported provider with tools and applications designed for OpenAI's API.
+
+### Starting the API Server
+
+#### From Command Line
+
+```bash
+# Start with default settings (port 8000)
+python -m webscout.Provider.OPENAI.api
+
+# Start with custom port
+python -m webscout.Provider.OPENAI.api --port 8080
+
+# Start with API key authentication
+python -m webscout.Provider.OPENAI.api --api-key "your-secret-key"
+
+# Specify a default provider
+python -m webscout.Provider.OPENAI.api --default-provider "Claude"
+
+# Run in debug mode
+python -m webscout.Provider.OPENAI.api --debug
+```
+
+#### From Python Code
+
+```python
+# Method 1: Using the helper function
+from webscout.Provider.OPENAI.api import start_server
+
+# Start with default settings
+start_server()
+
+# Start with custom settings
+start_server(port=8080, api_key="your-secret-key", default_provider="Claude")
+
+# Method 2: Using the run_api function for more control
+from webscout.Provider.OPENAI.api import run_api
+
+run_api(
+    host="0.0.0.0",
+    port=8080,
+    api_key="your-secret-key",
+    default_provider="Claude",
+    debug=True
+)
+```
+
+### Using the API
+
+Once the server is running, you can use it with any OpenAI client library or tool:
+
+```python
+# Using the OpenAI Python client
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="your-secret-key",  # Only needed if you set an API key
+    base_url="http://localhost:8000/v1"  # Point to your local server
+)
+
+# Chat completion
+response = client.chat.completions.create(
+    model="gpt-4",  # This can be any model name registered with Webscout
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Hello, how are you?"}
+    ]
+)
+
+print(response.choices[0].message.content)
+```
+
+### Using with cURL
+
+```bash
+# Basic chat completion request
+curl http://localhost:8000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer your-secret-key" \
+  -d '{
+    "model": "gpt-4",
+    "messages": [
+      {"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": "Hello, how are you?"}
+    ]
+  }'
+
+# List available models
+curl http://localhost:8000/v1/models \
+  -H "Authorization: Bearer your-secret-key"
+```
+
+### Available Endpoints
+
+- `GET /v1/models` - List all available models
+- `GET /v1/models/{model_name}` - Get information about a specific model
+- `POST /v1/chat/completions` - Create a chat completion
+
+</p>
+</details>
+
 <hr/>
 
 ## 🔍 Search Engines
@@ -618,30 +712,12 @@ Webscout offers a comprehensive collection of AI chat providers, giving you acce
 | `DeepInfra` | Various open models | Multiple model options |
 | `Cohere` | Cohere's language models | Command models |
 | `PerplexityLabs` | Perplexity AI | Web search integration |
-| `Anthropic` | Claude models | Long context windows |
 | `YEPCHAT` | Yep.com's AI | Streaming responses |
 | `ChatGPTClone` | ChatGPT-like interface | Multiple model options |
-| `TypeGPT` | TypeChat models | Code generation focus |
+| `TypeGPT` | TypeChat models | Multiple model options |
 
 </div>
 
-<details>
-<summary><b>Example: Using Duckchat</b></summary>
-<p>
-
-```python
-from webscout import WEBS
-
-# Initialize and use Duckchat
-with WEBS() as webs:
-    response = webs.chat(
-        "Explain quantum computing in simple terms",
-        model='gpt-4o-mini'  # Options: mixtral-8x7b, llama-3.1-70b, claude-3-haiku, etc.
-    )
-    print(response)
-```
-</p>
-</details>
 
 <details>
 <summary><b>Example: Using Meta AI</b></summary>
@@ -753,41 +829,7 @@ print(response)
 </p>
 </details>
 
-<hr/>
-
-## 👨‍💻 Advanced AI Interfaces
-
-<details open>
-<summary><b>Direct Model Access with LLM and VLM</b></summary>
-<p>
-
-Webscout provides direct interfaces to language and vision-language models through the `LLM` and `VLM` classes.
-
-```python
-from webscout.LLM import LLM, VLM
 
-# Text-only model interaction
-llm = LLM("meta-llama/Meta-Llama-3-70B-Instruct")
-response = llm.chat([
-    {"role": "user", "content": "Explain the concept of neural networks"}
-])
-print(response)
-
-# Vision-language model interaction
-vlm = VLM("cogvlm-grounding-generalist")
-response = vlm.chat([
-    {
-        "role": "user",
-        "content": [
-            {"type": "image", "image_url": "path/to/image.jpg"},
-            {"type": "text", "text": "Describe what you see in this image"}
-        ]
-    }
-])
-print(response)
-```
-</p>
-</details>
 
 <details open>
 <summary><b>GGUF Model Conversion</b></summary>