lm-deluge 0.0.35__tar.gz → 0.0.106__tar.gz

{lm_deluge-0.0.35/src/lm_deluge.egg-info → lm_deluge-0.0.106}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.35
+Version: 0.0.106
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10
@@ -9,7 +9,6 @@ License-File: LICENSE
 Requires-Dist: python-dotenv
 Requires-Dist: json5
 Requires-Dist: PyYAML
-Requires-Dist: pandas
 Requires-Dist: aiohttp
 Requires-Dist: tiktoken
 Requires-Dist: xxhash
@@ -21,8 +20,24 @@ Requires-Dist: bs4
 Requires-Dist: lxml
 Requires-Dist: pdf2image
 Requires-Dist: pillow
-Requires-Dist: fastmcp>=2.4
 Requires-Dist: rich
+Provides-Extra: aws
+Requires-Dist: boto3>=1.28.0; extra == "aws"
+Provides-Extra: docker
+Requires-Dist: docker>=7.0.0; extra == "docker"
+Provides-Extra: full-text-search
+Requires-Dist: tantivy>=0.21.0; extra == "full-text-search"
+Requires-Dist: lenlp>=0.1.0; extra == "full-text-search"
+Provides-Extra: sandbox
+Requires-Dist: modal>=0.64.0; extra == "sandbox"
+Requires-Dist: daytona-sdk>=0.1.4; extra == "sandbox"
+Requires-Dist: docker>=7.0.0; extra == "sandbox"
+Provides-Extra: server
+Requires-Dist: fastapi>=0.100.0; extra == "server"
+Requires-Dist: uvicorn>=0.20.0; extra == "server"
+Provides-Extra: dev
+Requires-Dist: ty; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
 Dynamic: license-file
 
 # lm-deluge
@@ -35,9 +50,9 @@ Dynamic: license-file
 - **Spray across models/providers** – Configure a client with multiple models from any provider(s), and sampling weights. The client samples a model for each request.
 - **Tool Use** – Unified API for defining tools for all providers, and creating tools automatically from python functions.
 - **MCP Support** – Instantiate a `Tool` from a local or remote MCP server so that any LLM can use it, whether or not that provider natively supports MCP.
-- **Computer Use** – We support Claude Computer Use via the computer_use argument to process_prompts_sync/async. It works with Anthropic's API; Bedrock's API is broken right now and rejects the tool definitions, but in principle this will work there too when Bedrock gets their sh*t together.
-- **Caching** – Save completions in a local or distributed cache to avoid repeated LLM calls to process the same input.
-- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our client or with the `openai` and `anthropic` packages.
+- **Computer Use** – We support computer use for all major providers, and have pre-fabricated tools to integrate with Kernel, TryCUA, and more.
+- **Local & Remote Caching** – Use Anthropic caching more easily with common patterns (system-only, tools-only, last N messages, etc.) Use client-side caching to save completions to avoid repeated LLM calls to process the same input.
+- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our `LLMClient` or with the `openai` and `anthropic` packages.
 - **Sync and async APIs** – Use the client from sync or async code.
 
 **STREAMING IS NOT IN SCOPE.** There are plenty of packages that let you stream chat completions across providers. The sole purpose of this package is to do very fast batch inference using APIs. Sorry!
@@ -50,7 +65,7 @@ Dynamic: license-file
 pip install lm-deluge
 ```
 
-The package relies on environment variables for API keys. Typical variables include `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `COHERE_API_KEY`, `META_API_KEY`, and `GOOGLE_API_KEY`. `LLMClient` will automatically load the `.env` file when imported; we recommend using that to set the environment variables. For Bedrock, you'll need to set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`.
+The package relies on environment variables for API keys. Typical variables include `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `COHERE_API_KEY`, `META_API_KEY`, and `GEMINI_API_KEY`. `LLMClient` will automatically load the `.env` file when imported; we recommend using that to set the environment variables. For Bedrock, you'll need to set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`.
 
 ## Quickstart
 
@@ -59,9 +74,9 @@ The package relies on environment variables for API keys. Typical variables incl
 ```python
 from lm_deluge import LLMClient
 
-client = LLMClient("gpt-4o-mini")
+client = LLMClient("gpt-4.1-mini")
 resps = client.process_prompts_sync(["Hello, world!"])
-print(resp[0].completion)
+print(resps[0].completion)
 ```
 
 ## Spraying Across Models
@@ -72,13 +87,13 @@ To distribute your requests across models, just provide a list of more than one
 from lm_deluge import LLMClient
 
 client = LLMClient(
-    ["gpt-4o-mini", "claude-3-haiku"],
+    ["gpt-4.1-mini", "claude-4.5-haiku"],
     max_requests_per_minute=10_000
 )
 resps = client.process_prompts_sync(
     ["Hello, ChatGPT!", "Hello, Claude!"]
 )
-print(resp[0].completion)
+print(resps[0].completion)
 ```
 
 ## Configuration
@@ -111,14 +126,17 @@ await client.process_prompts_async(
 
 ### Queueing individual prompts
 
-You can queue prompts one at a time and track progress explicitly:
+You can queue prompts one at a time and track progress explicitly. Iterate over
+results as they finish with `as_completed` (or gather them all at once with
+`wait_for_all`):
 
 ```python
 client = LLMClient("gpt-4.1-mini", progress="tqdm")
 client.open()
-task_id = client.start_nowait("hello there")
+client.start_nowait("hello there")
 # ... queue more tasks ...
-results = await client.wait_for_all()
+async for task_id, result in client.as_completed():
+    print(task_id, result.completion)
 client.close()
 ```
 
@@ -129,7 +147,7 @@ Constructing conversations to pass to models is notoriously annoying. Each provi
 ```python
 from lm_deluge import Message, Conversation
 
-prompt = Conversation.system("You are a helpful assistant.").add(
+prompt = Conversation().system("You are a helpful assistant.").add(
     Message.user("What's in this image?").add_image("tests/image.jpg")
 )
 
@@ -150,7 +168,7 @@ from lm_deluge import LLMClient, Conversation
 
 # Simple file upload
 client = LLMClient("gpt-4.1-mini")
-conversation = Conversation.user(
+conversation = Conversation().user(
     "Please summarize this document",
     file="path/to/document.pdf"
 )
@@ -159,7 +177,7 @@ resps = client.process_prompts_sync([conversation])
 # You can also create File objects for more control
 from lm_deluge import File
 file = File("path/to/report.pdf", filename="Q4_Report.pdf")
-conversation = Conversation.user("Analyze this financial report")
+conversation = Conversation().user("Analyze this financial report")
 conversation.messages[0].parts.append(file)
 ```
 
@@ -176,7 +194,7 @@ def get_weather(city: str) -> str:
     return f"The weather in {city} is sunny and 72°F"
 
 tool = Tool.from_function(get_weather)
-client = LLMClient("claude-3-haiku")
+client = LLMClient("claude-4.5-haiku")
 resps = client.process_prompts_sync(
     ["What's the weather in Paris?"],
     tools=[tool]
@@ -229,7 +247,7 @@ for tool_call in resps[0].tool_calls:
 import asyncio
 
 async def main():
-    conv = Conversation.user("List the files in the current directory")
+    conv = Conversation().user("List the files in the current directory")
     conv, resp = await client.run_agent_loop(conv, tools=tools)
     print(resp.content.completion)
 
@@ -245,12 +263,12 @@ from lm_deluge import LLMClient, Conversation, Message
 
 # Create a conversation with system message
 conv = (
-    Conversation.system("You are an expert Python developer with deep knowledge of async programming.")
+    Conversation().system("You are an expert Python developer with deep knowledge of async programming.")
     .add(Message.user("How do I use asyncio.gather?"))
 )
 
 # Use prompt caching to cache system message and tools
-client = LLMClient("claude-3-5-sonnet")
+client = LLMClient("claude-4.5-sonnet")
 resps = client.process_prompts_sync(
     [conv],
     cache="system_and_tools"  # Cache system message and any tools
@@ -291,7 +309,7 @@ We support structured outputs via `json_mode` parameter provided to `SamplingPar
 
 ## Built‑in tools
 
-The `lm_deluge.llm_tools` package exposes a few helper functions:
+The `lm_deluge.pipelines` module exposes a few helper functions that combine LLMClient with prompt and output parsing to accomplish tasks:
 
 - `extract` – structure text or images into a Pydantic model based on a schema.
 - `translate` – translate a list of strings to English.

{lm_deluge-0.0.35 → lm_deluge-0.0.106}/README.md

@@ -8,9 +8,9 @@
 - **Spray across models/providers** – Configure a client with multiple models from any provider(s), and sampling weights. The client samples a model for each request.
 - **Tool Use** – Unified API for defining tools for all providers, and creating tools automatically from python functions.
 - **MCP Support** – Instantiate a `Tool` from a local or remote MCP server so that any LLM can use it, whether or not that provider natively supports MCP.
-- **Computer Use** – We support Claude Computer Use via the computer_use argument to process_prompts_sync/async. It works with Anthropic's API; Bedrock's API is broken right now and rejects the tool definitions, but in principle this will work there too when Bedrock gets their sh*t together.
-- **Caching** – Save completions in a local or distributed cache to avoid repeated LLM calls to process the same input.
-- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our client or with the `openai` and `anthropic` packages.
+- **Computer Use** – We support computer use for all major providers, and have pre-fabricated tools to integrate with Kernel, TryCUA, and more.
+- **Local & Remote Caching** – Use Anthropic caching more easily with common patterns (system-only, tools-only, last N messages, etc.) Use client-side caching to save completions to avoid repeated LLM calls to process the same input.
+- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our `LLMClient` or with the `openai` and `anthropic` packages.
 - **Sync and async APIs** – Use the client from sync or async code.
 
 **STREAMING IS NOT IN SCOPE.** There are plenty of packages that let you stream chat completions across providers. The sole purpose of this package is to do very fast batch inference using APIs. Sorry!
@@ -23,7 +23,7 @@
 pip install lm-deluge
 ```
 
-The package relies on environment variables for API keys. Typical variables include `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `COHERE_API_KEY`, `META_API_KEY`, and `GOOGLE_API_KEY`. `LLMClient` will automatically load the `.env` file when imported; we recommend using that to set the environment variables. For Bedrock, you'll need to set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`.
+The package relies on environment variables for API keys. Typical variables include `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `COHERE_API_KEY`, `META_API_KEY`, and `GEMINI_API_KEY`. `LLMClient` will automatically load the `.env` file when imported; we recommend using that to set the environment variables. For Bedrock, you'll need to set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`.
 
 ## Quickstart
 
@@ -32,9 +32,9 @@ The package relies on environment variables for API keys. Typical variables incl
 ```python
 from lm_deluge import LLMClient
 
-client = LLMClient("gpt-4o-mini")
+client = LLMClient("gpt-4.1-mini")
 resps = client.process_prompts_sync(["Hello, world!"])
-print(resp[0].completion)
+print(resps[0].completion)
 ```
 
 ## Spraying Across Models
@@ -45,13 +45,13 @@ To distribute your requests across models, just provide a list of more than one
 from lm_deluge import LLMClient
 
 client = LLMClient(
-    ["gpt-4o-mini", "claude-3-haiku"],
+    ["gpt-4.1-mini", "claude-4.5-haiku"],
     max_requests_per_minute=10_000
 )
 resps = client.process_prompts_sync(
     ["Hello, ChatGPT!", "Hello, Claude!"]
 )
-print(resp[0].completion)
+print(resps[0].completion)
 ```
 
 ## Configuration
@@ -84,14 +84,17 @@ await client.process_prompts_async(
 
 ### Queueing individual prompts
 
-You can queue prompts one at a time and track progress explicitly:
+You can queue prompts one at a time and track progress explicitly. Iterate over
+results as they finish with `as_completed` (or gather them all at once with
+`wait_for_all`):
 
 ```python
 client = LLMClient("gpt-4.1-mini", progress="tqdm")
 client.open()
-task_id = client.start_nowait("hello there")
+client.start_nowait("hello there")
 # ... queue more tasks ...
-results = await client.wait_for_all()
+async for task_id, result in client.as_completed():
+    print(task_id, result.completion)
 client.close()
 ```
 
@@ -102,7 +105,7 @@ Constructing conversations to pass to models is notoriously annoying. Each provi
 ```python
 from lm_deluge import Message, Conversation
 
-prompt = Conversation.system("You are a helpful assistant.").add(
+prompt = Conversation().system("You are a helpful assistant.").add(
     Message.user("What's in this image?").add_image("tests/image.jpg")
 )
 
@@ -123,7 +126,7 @@ from lm_deluge import LLMClient, Conversation
 
 # Simple file upload
 client = LLMClient("gpt-4.1-mini")
-conversation = Conversation.user(
+conversation = Conversation().user(
     "Please summarize this document",
     file="path/to/document.pdf"
 )
@@ -132,7 +135,7 @@ resps = client.process_prompts_sync([conversation])
 # You can also create File objects for more control
 from lm_deluge import File
 file = File("path/to/report.pdf", filename="Q4_Report.pdf")
-conversation = Conversation.user("Analyze this financial report")
+conversation = Conversation().user("Analyze this financial report")
 conversation.messages[0].parts.append(file)
 ```
 
@@ -149,7 +152,7 @@ def get_weather(city: str) -> str:
     return f"The weather in {city} is sunny and 72°F"
 
 tool = Tool.from_function(get_weather)
-client = LLMClient("claude-3-haiku")
+client = LLMClient("claude-4.5-haiku")
 resps = client.process_prompts_sync(
     ["What's the weather in Paris?"],
     tools=[tool]
@@ -202,7 +205,7 @@ for tool_call in resps[0].tool_calls:
 import asyncio
 
 async def main():
-    conv = Conversation.user("List the files in the current directory")
+    conv = Conversation().user("List the files in the current directory")
     conv, resp = await client.run_agent_loop(conv, tools=tools)
     print(resp.content.completion)
 
@@ -218,12 +221,12 @@ from lm_deluge import LLMClient, Conversation, Message
 
 # Create a conversation with system message
 conv = (
-    Conversation.system("You are an expert Python developer with deep knowledge of async programming.")
+    Conversation().system("You are an expert Python developer with deep knowledge of async programming.")
     .add(Message.user("How do I use asyncio.gather?"))
 )
 
 # Use prompt caching to cache system message and tools
-client = LLMClient("claude-3-5-sonnet")
+client = LLMClient("claude-4.5-sonnet")
 resps = client.process_prompts_sync(
     [conv],
     cache="system_and_tools"  # Cache system message and any tools
@@ -264,7 +267,7 @@ We support structured outputs via `json_mode` parameter provided to `SamplingPar
 
 ## Built‑in tools
 
-The `lm_deluge.llm_tools` package exposes a few helper functions:
+The `lm_deluge.pipelines` module exposes a few helper functions that combine LLMClient with prompt and output parsing to accomplish tasks:
 
 - `extract` – structure text or images into a Pydantic model based on a schema.
 - `translate` – translate a list of strings to English.

{lm_deluge-0.0.35 → lm_deluge-0.0.106}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "wheel"]
 
 [project]
 name = "lm_deluge"
-version = "0.0.35"
+version = "0.0.106"
 authors = [{ name = "Benjamin Anderson", email = "ben@trytaylor.ai" }]
 description = "Python utility for using LLM API models."
 readme = "README.md"
@@ -15,7 +15,6 @@ dependencies = [
     "python-dotenv",
     "json5",
     "PyYAML",
-    "pandas",
     "aiohttp",
     "tiktoken",
     "xxhash",
@@ -27,6 +26,20 @@ dependencies = [
     "lxml",
     "pdf2image",
     "pillow",
-    "fastmcp>=2.4",
     "rich"
 ]
+
+[project.optional-dependencies]
+aws = ["boto3>=1.28.0"]
+docker = ["docker>=7.0.0"]
+full_text_search = ["tantivy>=0.21.0", "lenlp>=0.1.0"]
+sandbox = ["modal>=0.64.0", "daytona-sdk>=0.1.4", "docker>=7.0.0"]
+server = ["fastapi>=0.100.0", "uvicorn>=0.20.0"]
+dev = ["ty", "pre-commit"]
+
+[project.scripts]
+deluge = "lm_deluge.cli:main"
+deluge-server = "lm_deluge.server.__main__:main"
+
+[tool.setuptools.package-data]
+lm_deluge = ["skill/*.md"]

lm_deluge-0.0.106/src/lm_deluge/__init__.py

@@ -0,0 +1,19 @@
+from .client import AgentLoopCallback, APIResponse, LLMClient, SamplingParams
+from .prompt import Conversation, Message, File
+from .tool import Tool, MCPServer, Skill, execute_tool_calls
+
+# dotenv.load_dotenv() - don't do this, fucks with other packages
+
+__all__ = [
+    "LLMClient",
+    "SamplingParams",
+    "APIResponse",
+    "AgentLoopCallback",
+    "Conversation",
+    "Message",
+    "Tool",
+    "MCPServer",
+    "Skill",
+    "File",
+    "execute_tool_calls",
+]