prompture 0.0.40.dev1__tar.gz → 0.0.41.dev1__tar.gz

{prompture-0.0.40.dev1 → prompture-0.0.41.dev1}/.env.copy

@@ -60,6 +60,24 @@ OPENROUTER_MODEL=openai/gpt-3.5-turbo
 GROK_API_KEY=your-api-key-here
 GROK_MODEL=grok-4-fast-reasoning
 
+# Moonshot AI (Kimi) Configuration
+# Required if AI_PROVIDER=moonshot
+MOONSHOT_API_KEY=
+MOONSHOT_MODEL=kimi-k2-0905-preview
+MOONSHOT_ENDPOINT=https://api.moonshot.ai/v1
+
+# Z.ai (Zhipu AI) Configuration
+# Required if AI_PROVIDER=zai
+ZHIPU_API_KEY=
+ZHIPU_MODEL=glm-4.7
+ZHIPU_ENDPOINT=https://api.z.ai/api/paas/v4
+
+# ModelScope (Alibaba Cloud) Configuration
+# Required if AI_PROVIDER=modelscope
+MODELSCOPE_API_KEY=
+MODELSCOPE_MODEL=Qwen/Qwen3-235B-A22B-Instruct-2507
+MODELSCOPE_ENDPOINT=https://api-inference.modelscope.cn/v1
+
 # AirLLM Configuration
 AIRLLM_MODEL=meta-llama/Llama-2-7b-hf
 AIRLLM_COMPRESSION=

{prompture-0.0.40.dev1/prompture.egg-info → prompture-0.0.41.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: prompture
-Version: 0.0.40.dev1
+Version: 0.0.41.dev1
 Summary: Ask LLMs to return structured JSON and run cross-model tests. API-first.
 Author-email: Juan Denis <juan@vene.co>
 License-Expression: MIT

{prompture-0.0.40.dev1 → prompture-0.0.41.dev1}/prompture/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.0.40.dev1'
-__version_tuple__ = version_tuple = (0, 0, 40, 'dev1')
+__version__ = version = '0.0.41.dev1'
+__version_tuple__ = version_tuple = (0, 0, 41, 'dev1')
 
 __commit_id__ = commit_id = None

{prompture-0.0.40.dev1 → prompture-0.0.41.dev1}/prompture/drivers/__init__.py

@@ -37,10 +37,13 @@ from .async_groq_driver import AsyncGroqDriver
 from .async_hugging_driver import AsyncHuggingFaceDriver
 from .async_lmstudio_driver import AsyncLMStudioDriver
 from .async_local_http_driver import AsyncLocalHTTPDriver
+from .async_modelscope_driver import AsyncModelScopeDriver
+from .async_moonshot_driver import AsyncMoonshotDriver
 from .async_ollama_driver import AsyncOllamaDriver
 from .async_openai_driver import AsyncOpenAIDriver
 from .async_openrouter_driver import AsyncOpenRouterDriver
 from .async_registry import ASYNC_DRIVER_REGISTRY, get_async_driver, get_async_driver_for_model
+from .async_zai_driver import AsyncZaiDriver
 from .azure_driver import AzureDriver
 from .claude_driver import ClaudeDriver
 from .google_driver import GoogleDriver
@@ -48,6 +51,8 @@ from .grok_driver import GrokDriver
 from .groq_driver import GroqDriver
 from .lmstudio_driver import LMStudioDriver
 from .local_http_driver import LocalHTTPDriver
+from .modelscope_driver import ModelScopeDriver
+from .moonshot_driver import MoonshotDriver
 from .ollama_driver import OllamaDriver
 from .openai_driver import OpenAIDriver
 from .openrouter_driver import OpenRouterDriver
@@ -65,6 +70,7 @@ from .registry import (
     unregister_async_driver,
     unregister_driver,
 )
+from .zai_driver import ZaiDriver
 
 # Register built-in sync drivers
 register_driver(
@@ -123,6 +129,33 @@ register_driver(
     lambda model=None: GrokDriver(api_key=settings.grok_api_key, model=model or settings.grok_model),
     overwrite=True,
 )
+register_driver(
+    "moonshot",
+    lambda model=None: MoonshotDriver(
+        api_key=settings.moonshot_api_key,
+        model=model or settings.moonshot_model,
+        endpoint=settings.moonshot_endpoint,
+    ),
+    overwrite=True,
+)
+register_driver(
+    "modelscope",
+    lambda model=None: ModelScopeDriver(
+        api_key=settings.modelscope_api_key,
+        model=model or settings.modelscope_model,
+        endpoint=settings.modelscope_endpoint,
+    ),
+    overwrite=True,
+)
+register_driver(
+    "zai",
+    lambda model=None: ZaiDriver(
+        api_key=settings.zhipu_api_key,
+        model=model or settings.zhipu_model,
+        endpoint=settings.zhipu_endpoint,
+    ),
+    overwrite=True,
+)
 register_driver(
     "airllm",
     lambda model=None: AirLLMDriver(
@@ -197,9 +230,12 @@ __all__ = [
     "AsyncHuggingFaceDriver",
     "AsyncLMStudioDriver",
     "AsyncLocalHTTPDriver",
+    "AsyncModelScopeDriver",
+    "AsyncMoonshotDriver",
     "AsyncOllamaDriver",
     "AsyncOpenAIDriver",
     "AsyncOpenRouterDriver",
+    "AsyncZaiDriver",
     "AzureDriver",
     "ClaudeDriver",
     "GoogleDriver",
@@ -207,9 +243,12 @@ __all__ = [
     "GroqDriver",
     "LMStudioDriver",
     "LocalHTTPDriver",
+    "ModelScopeDriver",
+    "MoonshotDriver",
     "OllamaDriver",
     "OpenAIDriver",
     "OpenRouterDriver",
+    "ZaiDriver",
     "get_async_driver",
     "get_async_driver_for_model",
     # Factory functions

prompture-0.0.41.dev1/prompture/drivers/async_modelscope_driver.py

@@ -0,0 +1,286 @@
+"""Async ModelScope (Alibaba Cloud) driver using httpx.
+
+No hardcoded pricing — ModelScope's free tier has no per-token cost.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from collections.abc import AsyncIterator
+from typing import Any
+
+import httpx
+
+from ..async_driver import AsyncDriver
+from ..cost_mixin import CostMixin
+from .modelscope_driver import ModelScopeDriver
+
+
+class AsyncModelScopeDriver(CostMixin, AsyncDriver):
+    supports_json_mode = True
+    supports_json_schema = False
+    supports_tool_use = True
+    supports_streaming = True
+    supports_vision = False
+
+    MODEL_PRICING = ModelScopeDriver.MODEL_PRICING
+
+    def __init__(
+        self,
+        api_key: str | None = None,
+        model: str = "Qwen/Qwen3-235B-A22B-Instruct-2507",
+        endpoint: str = "https://api-inference.modelscope.cn/v1",
+    ):
+        self.api_key = api_key or os.getenv("MODELSCOPE_API_KEY")
+        if not self.api_key:
+            raise ValueError("ModelScope API key not found. Set MODELSCOPE_API_KEY env var.")
+        self.model = model
+        self.base_url = endpoint.rstrip("/")
+        self.headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json",
+        }
+
+    supports_messages = True
+
+    async def generate(self, prompt: str, options: dict[str, Any]) -> dict[str, Any]:
+        messages = [{"role": "user", "content": prompt}]
+        return await self._do_generate(messages, options)
+
+    async def generate_messages(self, messages: list[dict[str, str]], options: dict[str, Any]) -> dict[str, Any]:
+        return await self._do_generate(messages, options)
+
+    async def _do_generate(self, messages: list[dict[str, str]], options: dict[str, Any]) -> dict[str, Any]:
+        model = options.get("model", self.model)
+
+        model_config = self._get_model_config("modelscope", model)
+        tokens_param = model_config["tokens_param"]
+        supports_temperature = model_config["supports_temperature"]
+
+        self._validate_model_capabilities(
+            "modelscope",
+            model,
+            using_json_schema=bool(options.get("json_schema")),
+        )
+
+        opts = {"temperature": 1.0, "max_tokens": 512, **options}
+
+        data: dict[str, Any] = {
+            "model": model,
+            "messages": messages,
+        }
+        data[tokens_param] = opts.get("max_tokens", 512)
+
+        if supports_temperature and "temperature" in opts:
+            data["temperature"] = opts["temperature"]
+
+        if options.get("json_mode"):
+            data["response_format"] = {"type": "json_object"}
+
+        async with httpx.AsyncClient() as client:
+            try:
+                response = await client.post(
+                    f"{self.base_url}/chat/completions",
+                    headers=self.headers,
+                    json=data,
+                    timeout=120,
+                )
+                response.raise_for_status()
+                resp = response.json()
+            except httpx.HTTPStatusError as e:
+                error_msg = f"ModelScope API request failed: {e!s}"
+                raise RuntimeError(error_msg) from e
+            except Exception as e:
+                raise RuntimeError(f"ModelScope API request failed: {e!s}") from e
+
+        usage = resp.get("usage", {})
+        prompt_tokens = usage.get("prompt_tokens", 0)
+        completion_tokens = usage.get("completion_tokens", 0)
+        total_tokens = usage.get("total_tokens", 0)
+
+        total_cost = self._calculate_cost("modelscope", model, prompt_tokens, completion_tokens)
+
+        meta = {
+            "prompt_tokens": prompt_tokens,
+            "completion_tokens": completion_tokens,
+            "total_tokens": total_tokens,
+            "cost": round(total_cost, 6),
+            "raw_response": resp,
+            "model_name": model,
+        }
+
+        text = resp["choices"][0]["message"]["content"]
+        return {"text": text, "meta": meta}
+
+    # ------------------------------------------------------------------
+    # Tool use
+    # ------------------------------------------------------------------
+
+    async def generate_messages_with_tools(
+        self,
+        messages: list[dict[str, Any]],
+        tools: list[dict[str, Any]],
+        options: dict[str, Any],
+    ) -> dict[str, Any]:
+        """Generate a response that may include tool calls."""
+        model = options.get("model", self.model)
+        model_config = self._get_model_config("modelscope", model)
+        tokens_param = model_config["tokens_param"]
+        supports_temperature = model_config["supports_temperature"]
+
+        self._validate_model_capabilities("modelscope", model, using_tool_use=True)
+
+        opts = {"temperature": 1.0, "max_tokens": 512, **options}
+
+        data: dict[str, Any] = {
+            "model": model,
+            "messages": messages,
+            "tools": tools,
+        }
+        data[tokens_param] = opts.get("max_tokens", 512)
+
+        if supports_temperature and "temperature" in opts:
+            data["temperature"] = opts["temperature"]
+
+        if "tool_choice" in options:
+            data["tool_choice"] = options["tool_choice"]
+
+        async with httpx.AsyncClient() as client:
+            try:
+                response = await client.post(
+                    f"{self.base_url}/chat/completions",
+                    headers=self.headers,
+                    json=data,
+                    timeout=120,
+                )
+                response.raise_for_status()
+                resp = response.json()
+            except httpx.HTTPStatusError as e:
+                error_msg = f"ModelScope API request failed: {e!s}"
+                raise RuntimeError(error_msg) from e
+            except Exception as e:
+                raise RuntimeError(f"ModelScope API request failed: {e!s}") from e
+
+        usage = resp.get("usage", {})
+        prompt_tokens = usage.get("prompt_tokens", 0)
+        completion_tokens = usage.get("completion_tokens", 0)
+        total_tokens = usage.get("total_tokens", 0)
+        total_cost = self._calculate_cost("modelscope", model, prompt_tokens, completion_tokens)
+
+        meta = {
+            "prompt_tokens": prompt_tokens,
+            "completion_tokens": completion_tokens,
+            "total_tokens": total_tokens,
+            "cost": round(total_cost, 6),
+            "raw_response": resp,
+            "model_name": model,
+        }
+
+        choice = resp["choices"][0]
+        text = choice["message"].get("content") or ""
+        stop_reason = choice.get("finish_reason")
+
+        tool_calls_out: list[dict[str, Any]] = []
+        for tc in choice["message"].get("tool_calls", []):
+            try:
+                args = json.loads(tc["function"]["arguments"])
+            except (json.JSONDecodeError, TypeError):
+                args = {}
+            tool_calls_out.append(
+                {
+                    "id": tc["id"],
+                    "name": tc["function"]["name"],
+                    "arguments": args,
+                }
+            )
+
+        return {
+            "text": text,
+            "meta": meta,
+            "tool_calls": tool_calls_out,
+            "stop_reason": stop_reason,
+        }
+
+    # ------------------------------------------------------------------
+    # Streaming
+    # ------------------------------------------------------------------
+
+    async def generate_messages_stream(
+        self,
+        messages: list[dict[str, Any]],
+        options: dict[str, Any],
+    ) -> AsyncIterator[dict[str, Any]]:
+        """Yield response chunks via ModelScope streaming API."""
+        model = options.get("model", self.model)
+        model_config = self._get_model_config("modelscope", model)
+        tokens_param = model_config["tokens_param"]
+        supports_temperature = model_config["supports_temperature"]
+
+        opts = {"temperature": 1.0, "max_tokens": 512, **options}
+
+        data: dict[str, Any] = {
+            "model": model,
+            "messages": messages,
+            "stream": True,
+            "stream_options": {"include_usage": True},
+        }
+        data[tokens_param] = opts.get("max_tokens", 512)
+
+        if supports_temperature and "temperature" in opts:
+            data["temperature"] = opts["temperature"]
+
+        full_text = ""
+        prompt_tokens = 0
+        completion_tokens = 0
+
+        async with (
+            httpx.AsyncClient() as client,
+            client.stream(
+                "POST",
+                f"{self.base_url}/chat/completions",
+                headers=self.headers,
+                json=data,
+                timeout=120,
+            ) as response,
+        ):
+            response.raise_for_status()
+            async for line in response.aiter_lines():
+                if not line or not line.startswith("data: "):
+                    continue
+                payload = line[len("data: ") :]
+                if payload.strip() == "[DONE]":
+                    break
+                try:
+                    chunk = json.loads(payload)
+                except json.JSONDecodeError:
+                    continue
+
+                usage = chunk.get("usage")
+                if usage:
+                    prompt_tokens = usage.get("prompt_tokens", 0)
+                    completion_tokens = usage.get("completion_tokens", 0)
+
+                choices = chunk.get("choices", [])
+                if choices:
+                    delta = choices[0].get("delta", {})
+                    content = delta.get("content", "")
+                    if content:
+                        full_text += content
+                        yield {"type": "delta", "text": content}
+
+        total_tokens = prompt_tokens + completion_tokens
+        total_cost = self._calculate_cost("modelscope", model, prompt_tokens, completion_tokens)
+
+        yield {
+            "type": "done",
+            "text": full_text,
+            "meta": {
+                "prompt_tokens": prompt_tokens,
+                "completion_tokens": completion_tokens,
+                "total_tokens": total_tokens,
+                "cost": round(total_cost, 6),
+                "raw_response": {},
+                "model_name": model,
+            },
+        }