chatlas 0.8.1__tar.gz → 0.9.1__tar.gz

{chatlas-0.8.1 → chatlas-0.9.1}/.github/workflows/check-update-types.yml

@@ -1,4 +1,4 @@
-name: Test - Python
+name: Check Provider Types
 
 on:
   workflow_dispatch:

chatlas-0.9.1/.github/workflows/update-pricing.yml

@@ -0,0 +1,38 @@
+name: Update Pricing
+
+on:
+    workflow_dispatch:
+    pull_request:
+        types: [opened, synchronize, reopened, ready_for_review]
+
+jobs:
+    check-pricing:
+        name: Check for pricing updates in Ellmer
+        runs-on: ubuntu-latest
+
+        steps:
+
+            - name: Checkout current prices.json in chatlas
+              uses: actions/checkout@v4
+              with:
+                sparse-checkout: /chatlas/data/prices.json
+                sparse-checkout-cone-mode: false
+                path: main
+
+            - name: Get Ellmer prices.json
+              uses: actions/checkout@v4
+              with:
+                sparse-checkout: /data-raw/prices.json
+                sparse-checkout-cone-mode: false
+                repository: tidyverse/ellmer
+                path: ellmer
+            
+            - name: Check for differences
+              run: |
+                echo "Checking diff between prices.json"
+                git diff --no-index --stat ellmer/data-raw/prices.json main/chatlas/data/prices.json
+                if [[ -n $(git diff --no-index --stat ellmer/data-raw/prices.json main/chatlas/data/prices.json) ]]; then
+                    echo "Changes detected:"
+                    echo "::error::Ellmer's prices.json does not match the current Chatlas prices.json"
+                    exit 1
+                fi

{chatlas-0.8.1 → chatlas-0.9.1}/.gitignore

@@ -10,8 +10,5 @@ sandbox/
 
 /.luarc.json
 
-# Automatically generated by docs/index.py
-docs/index.qmd
-
 # setuptools_scm
 chatlas/_version.py

{chatlas-0.8.1 → chatlas-0.9.1}/CHANGELOG.md

@@ -7,6 +7,60 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 -->
 
+## [0.9.1] - 2025-07-09
+
+### Bug fixes
+
+* Fixed an issue where `.chat()` wasn't streaming output properly in (the latest build of) Positron's Jupyter notebook. (#131)
+
+* Needless warnings and errors are no longer thrown when model pricing info is unavailable. (#132)
+
+## [0.9.0] - 2025-07-02
+
+### New features
+
+* `Chat` gains a handful of new methods: 
+    * `.register_mcp_tools_http_stream_async()` and `.register_mcp_tools_stdio_async()`: for registering tools from a [MCP server](https://modelcontextprotocol.io/). (#39)
+    * `.get_tools()` and `.set_tools()`: for fine-grained control over registered tools. (#39)
+    * `.set_model_params()`: for setting common LLM parameters in a model-agnostic fashion. (#127)
+    * `.get_cost()`: to get the estimated cost of the chat. Only popular models are supported, but you can also supply your own token prices. (#106)
+    * `.add_turn()`: to add `Turn`(s) to the current chat history. (#126)
+* Tool functions passed to `.register_tool()` can now `yield` numerous results. (#39)
+* A `ContentToolResultImage` content class was added for returning images from tools. It is currently only works with `ChatAnthropic`. (#39)
+* A `Tool` can now be constructed from a pre-existing tool schema (via a new `__init__` method). (#39)
+* The `Chat.app()` method gains a `host` parameter. (#122) 
+* `ChatGithub()` now supports the more standard `GITHUB_TOKEN` environment variable for storing the API key. (#123)
+
+### Changes
+
+#### Breaking Changes
+
+* `Chat` constructors (`ChatOpenAI()`, `ChatAnthropic()`, etc) no longer have a `turns` keyword parameter. Use the `.set_turns()` method instead to set the (initial) chat history. (#126)
+* `Chat`'s `.tokens()` methods have been removed in favor of `.get_tokens()` which returns both cumulative tokens in the turn and discrete tokens. (#106)
+
+#### Other Changes
+
+* `Tool`'s constructor no longer takes a function as input. Use the new `.from_func()` method instead to create a `Tool` from a function. (#39)
+* `.register_tool()` now throws an exception when the tool has the same name as an already registered tool. Set the new `force` parameter to `True` to force the registration. (#39)
+
+### Improvements
+
+* `ChatGoogle()` and `ChatVertex()` now default to Gemini 2.5 (instead of 2.0). (#125)
+* `ChatOpenAI()` and `ChatGithub()` now default to GPT 4.1 (instead of 4o). (#115)
+* `ChatAnthropic()` now supports `content_image_url()`. (#112)
+* HTML styling improvements for `ContentToolResult` and `ContentToolRequest`. (#39)
+* `Chat`'s representation now includes cost information if it can be calculated. (#106)
+* `token_usage()` includes cost if it can be calculated. (#106)
+
+### Bug fixes
+
+* Fixed an issue where `httpx` client customization (e.g., `ChatOpenAI(kwargs = {"http_client": httpx.Client()})`) wasn't working as expected (#108)
+
+### Developer APIs
+
+* The base `Provider` class now includes a `name` and `model` property. In order for them to work properly, provider implementations should pass a `name` and `model` along to the `__init__()` method. (#106)
+* `Provider` implementations must implement two new abstract methods: `translate_model_params()` and `supported_model_params()`.
+
 ## [0.8.1] - 2025-05-30
 
 * Fixed `@overload` definitions for `.stream()` and `.stream_async()`.

chatlas-0.9.1/PKG-INFO

@@ -0,0 +1,141 @@
+Metadata-Version: 2.4
+Name: chatlas
+Version: 0.9.1
+Summary: A simple and consistent interface for chatting with LLMs
+Project-URL: Homepage, https://posit-dev.github.io/chatlas
+Project-URL: Documentation, https://posit-dev.github.io/chatlas
+Project-URL: Repository, https://github.com/posit-dev/chatlas
+Project-URL: Issues, https://github.com/posit-dev/chatlas/issues/
+Project-URL: Changelog, https://github.com/posit-dev/chatlas/blob/main/CHANGELOG.md
+Author-email: Carson Sievert <carson@posit.co>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.9
+Requires-Dist: jinja2
+Requires-Dist: openai
+Requires-Dist: orjson
+Requires-Dist: pydantic>=2.0
+Requires-Dist: requests
+Requires-Dist: rich
+Provides-Extra: anthropic
+Requires-Dist: anthropic; extra == 'anthropic'
+Provides-Extra: azure-openai
+Provides-Extra: bedrock-anthropic
+Requires-Dist: anthropic[bedrock]; extra == 'bedrock-anthropic'
+Provides-Extra: databricks
+Requires-Dist: databricks-sdk; extra == 'databricks'
+Provides-Extra: dev
+Requires-Dist: anthropic[bedrock]; extra == 'dev'
+Requires-Dist: databricks-sdk; extra == 'dev'
+Requires-Dist: google-genai>=1.14.0; extra == 'dev'
+Requires-Dist: htmltools; extra == 'dev'
+Requires-Dist: matplotlib; extra == 'dev'
+Requires-Dist: numpy>1.24.4; extra == 'dev'
+Requires-Dist: openai; extra == 'dev'
+Requires-Dist: pillow; extra == 'dev'
+Requires-Dist: python-dotenv; extra == 'dev'
+Requires-Dist: ruff>=0.6.5; extra == 'dev'
+Requires-Dist: shiny; extra == 'dev'
+Requires-Dist: snowflake-ml-python>=1.8.4; extra == 'dev'
+Requires-Dist: tenacity; extra == 'dev'
+Requires-Dist: tiktoken; extra == 'dev'
+Requires-Dist: torch; (python_version <= '3.11') and extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: griffe>=1; extra == 'docs'
+Requires-Dist: ipykernel; extra == 'docs'
+Requires-Dist: ipywidgets; extra == 'docs'
+Requires-Dist: nbclient; extra == 'docs'
+Requires-Dist: nbformat; extra == 'docs'
+Requires-Dist: numpy; extra == 'docs'
+Requires-Dist: pandas; extra == 'docs'
+Requires-Dist: pyyaml; extra == 'docs'
+Requires-Dist: quartodoc>=0.7; extra == 'docs'
+Requires-Dist: sentence-transformers; extra == 'docs'
+Provides-Extra: github
+Provides-Extra: google
+Requires-Dist: google-genai>=1.14.0; extra == 'google'
+Provides-Extra: groq
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.4.0; (python_version >= '3.10') and extra == 'mcp'
+Provides-Extra: ollama
+Provides-Extra: openai
+Provides-Extra: perplexity
+Provides-Extra: snowflake
+Requires-Dist: snowflake-ml-python; extra == 'snowflake'
+Provides-Extra: test
+Requires-Dist: pyright>=1.1.379; extra == 'test'
+Requires-Dist: pytest-asyncio; extra == 'test'
+Requires-Dist: pytest>=8.3.2; extra == 'test'
+Requires-Dist: syrupy>=4; extra == 'test'
+Provides-Extra: vertex
+Requires-Dist: google-genai>=1.14.0; extra == 'vertex'
+Description-Content-Type: text/markdown
+
+# chatlas <a href="https://posit-dev.github.io/chatlas"><img src="docs/logos/hex/logo.png" align="right" height="138" alt="chatlas website" /></a>
+
+<p>
+<!-- badges start -->
+<a href="https://pypi.org/project/chatlas/"><img alt="PyPI" src="https://img.shields.io/pypi/v/chatlas?logo=python&logoColor=white&color=orange"></a>
+<a href="https://choosealicense.com/licenses/mit/"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="MIT License"></a>
+<a href="https://pypi.org/project/chatlas"><img src="https://img.shields.io/pypi/pyversions/chatlas.svg" alt="versions"></a>
+<a href="https://github.com/posit-dev/chatlas"><img src="https://github.com/posit-dev/chatlas/actions/workflows/test.yml/badge.svg?branch=main" alt="Python Tests"></a>
+<!-- badges end -->
+</p>
+
+Your friendly guide to building LLM chat apps in Python with less effort and more clarity.
+
+## Install
+
+Install the latest stable release [from PyPI](https://pypi.org/project/chatlas/):
+
+```bash
+pip install -U chatlas
+```
+
+Or, install the latest development version from GitHub:
+
+```bash
+pip install -U git+https://github.com/posit-dev/chatlas
+```
+
+## Quick start
+
+Get started in 3 simple steps:
+
+1. Choose a model provider, such as [ChatOpenAI](https://posit-dev.github.io/chatlas/reference/ChatOpenAI.html) or [ChatAnthropic](https://posit-dev.github.io/chatlas/reference/ChatAnthropic.html).
+2. Visit the provider's [reference](https://posit-dev.github.io/chatlas/reference) page to get setup with necessary credentials.
+3. Create the relevant `Chat` client and start chatting!
+
+```python
+from chatlas import ChatOpenAI
+
+# Optional (but recommended) model and system_prompt
+chat = ChatOpenAI(
+    model="gpt-4.1-mini",
+    system_prompt="You are a helpful assistant.",
+)
+
+# Optional tool registration
+def get_current_weather(lat: float, lng: float):
+    "Get the current weather for a given location."
+    return "sunny"
+
+chat.register_tool(get_current_weather)
+
+# Send user prompt to the model for a response.
+chat.chat("How's the weather in San Francisco?")
+```
+
+
+<img src="docs/images/chatlas-hello.png" alt="Model response output to the user query: 'How's the weather in San Francisco?'" width="67%" style="display: block; margin-left: auto; margin-right: auto">
+
+
+Learn more at <https://posit-dev.github.io/chatlas>

chatlas-0.9.1/README.md

@@ -0,0 +1,60 @@
+# chatlas <a href="https://posit-dev.github.io/chatlas"><img src="docs/logos/hex/logo.png" align="right" height="138" alt="chatlas website" /></a>
+
+<p>
+<!-- badges start -->
+<a href="https://pypi.org/project/chatlas/"><img alt="PyPI" src="https://img.shields.io/pypi/v/chatlas?logo=python&logoColor=white&color=orange"></a>
+<a href="https://choosealicense.com/licenses/mit/"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="MIT License"></a>
+<a href="https://pypi.org/project/chatlas"><img src="https://img.shields.io/pypi/pyversions/chatlas.svg" alt="versions"></a>
+<a href="https://github.com/posit-dev/chatlas"><img src="https://github.com/posit-dev/chatlas/actions/workflows/test.yml/badge.svg?branch=main" alt="Python Tests"></a>
+<!-- badges end -->
+</p>
+
+Your friendly guide to building LLM chat apps in Python with less effort and more clarity.
+
+## Install
+
+Install the latest stable release [from PyPI](https://pypi.org/project/chatlas/):
+
+```bash
+pip install -U chatlas
+```
+
+Or, install the latest development version from GitHub:
+
+```bash
+pip install -U git+https://github.com/posit-dev/chatlas
+```
+
+## Quick start
+
+Get started in 3 simple steps:
+
+1. Choose a model provider, such as [ChatOpenAI](https://posit-dev.github.io/chatlas/reference/ChatOpenAI.html) or [ChatAnthropic](https://posit-dev.github.io/chatlas/reference/ChatAnthropic.html).
+2. Visit the provider's [reference](https://posit-dev.github.io/chatlas/reference) page to get setup with necessary credentials.
+3. Create the relevant `Chat` client and start chatting!
+
+```python
+from chatlas import ChatOpenAI
+
+# Optional (but recommended) model and system_prompt
+chat = ChatOpenAI(
+    model="gpt-4.1-mini",
+    system_prompt="You are a helpful assistant.",
+)
+
+# Optional tool registration
+def get_current_weather(lat: float, lng: float):
+    "Get the current weather for a given location."
+    return "sunny"
+
+chat.register_tool(get_current_weather)
+
+# Send user prompt to the model for a response.
+chat.chat("How's the weather in San Francisco?")
+```
+
+
+<img src="docs/images/chatlas-hello.png" alt="Model response output to the user query: 'How's the weather in San Francisco?'" width="67%" style="display: block; margin-left: auto; margin-right: auto">
+
+
+Learn more at <https://posit-dev.github.io/chatlas>

{chatlas-0.8.1 → chatlas-0.9.1}/chatlas/__init__.py

@@ -2,7 +2,7 @@ from . import types
 from ._anthropic import ChatAnthropic, ChatBedrockAnthropic
 from ._auto import ChatAuto
 from ._chat import Chat
-from ._content import ContentToolRequest, ContentToolResult
+from ._content import ContentToolRequest, ContentToolResult, ContentToolResultImage
 from ._content_image import content_image_file, content_image_plot, content_image_url
 from ._content_pdf import content_pdf_file, content_pdf_url
 from ._databricks import ChatDatabricks
@@ -46,6 +46,7 @@ __all__ = (
     "content_pdf_url",
     "ContentToolRequest",
     "ContentToolResult",
+    "ContentToolResultImage",
     "interpolate",
     "interpolate_file",
     "Provider",

{chatlas-0.8.1 → chatlas-0.9.1}/chatlas/_anthropic.py

@@ -17,12 +17,15 @@ from ._content import (
     ContentText,
     ContentToolRequest,
     ContentToolResult,
+    ContentToolResultImage,
+    ContentToolResultResource,
 )
 from ._logging import log_model_default
-from ._provider import Provider
+from ._provider import Provider, StandardModelParamNames, StandardModelParams
 from ._tokens import tokens_log
 from ._tools import Tool, basemodel_to_param_schema
-from ._turn import Turn, normalize_turns, user_turn
+from ._turn import Turn, user_turn
+from ._utils import split_http_client_kwargs
 
 if TYPE_CHECKING:
     from anthropic.types import (
@@ -58,7 +61,6 @@ else:
 def ChatAnthropic(
     *,
     system_prompt: Optional[str] = None,
-    turns: Optional[list[Turn]] = None,
     model: "Optional[ModelParam]" = None,
     api_key: Optional[str] = None,
     max_tokens: int = 4096,
@@ -104,13 +106,6 @@ def ChatAnthropic(
     ----------
     system_prompt
         A system prompt to set the behavior of the assistant.
-    turns
-        A list of turns to start the chat with (i.e., continuing a previous
-        conversation). If not provided, the conversation begins from scratch. Do
-        not provide non-None values for both `turns` and `system_prompt`. Each
-        message in the list should be a dictionary with at least `role` (usually
-        `system`, `user`, or `assistant`, but `tool` is also possible). Normally
-        there is also a `content` field, which is a string.
     model
         The model to use for the chat. The default, None, will pick a reasonable
         default, and warn you about it. We strongly recommend explicitly
@@ -177,22 +172,23 @@ def ChatAnthropic(
             max_tokens=max_tokens,
             kwargs=kwargs,
         ),
-        turns=normalize_turns(
-            turns or [],
-            system_prompt,
-        ),
+        system_prompt=system_prompt,
     )
 
 
-class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
+class AnthropicProvider(
+    Provider[Message, RawMessageStreamEvent, Message, "SubmitInputArgs"]
+):
     def __init__(
         self,
         *,
-        max_tokens: int,
+        max_tokens: int = 4096,
         model: str,
-        api_key: str | None,
+        api_key: Optional[str] = None,
+        name: str = "Anthropic",
         kwargs: Optional["ChatClientArgs"] = None,
     ):
+        super().__init__(name=name, model=model)
         try:
             from anthropic import Anthropic, AsyncAnthropic
         except ImportError:
@@ -200,8 +196,6 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
                 "`ChatAnthropic()` requires the `anthropic` package. "
                 "You can install it with 'pip install anthropic'."
             )
-
-        self._model = model
         self._max_tokens = max_tokens
 
         kwargs_full: "ChatClientArgs" = {
@@ -209,9 +203,11 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
             **(kwargs or {}),
         }
 
+        sync_kwargs, async_kwargs = split_http_client_kwargs(kwargs_full)
+
         # TODO: worth bringing in sync types?
-        self._client = Anthropic(**kwargs_full)  # type: ignore
-        self._async_client = AsyncAnthropic(**kwargs_full)
+        self._client = Anthropic(**sync_kwargs)  # type: ignore
+        self._async_client = AsyncAnthropic(**async_kwargs)
 
     @overload
     def chat_perform(
@@ -301,7 +297,7 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
                 """Extract structured data"""
                 pass
 
-            data_model_tool = Tool(_structured_tool_call)
+            data_model_tool = Tool.from_func(_structured_tool_call)
 
             data_model_tool.schema["function"]["parameters"] = {
                 "type": "object",
@@ -322,7 +318,7 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
         kwargs_full: "SubmitInputArgs" = {
             "stream": stream,
             "messages": self._as_message_params(turns),
-            "model": self._model,
+            "model": self.model,
             "max_tokens": self._max_tokens,
             "tools": tool_schemas,
             **(kwargs or {}),
@@ -435,6 +431,34 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
 
         return {arg: kwargs[arg] for arg in args_to_keep if arg in kwargs}
 
+    def translate_model_params(self, params: StandardModelParams) -> "SubmitInputArgs":
+        res: "SubmitInputArgs" = {}
+        if "temperature" in params:
+            res["temperature"] = params["temperature"]
+
+        if "top_p" in params:
+            res["top_p"] = params["top_p"]
+
+        if "top_k" in params:
+            res["top_k"] = params["top_k"]
+
+        if "max_tokens" in params:
+            res["max_tokens"] = params["max_tokens"]
+
+        if "stop_sequences" in params:
+            res["stop_sequences"] = params["stop_sequences"]
+
+        return res
+
+    def supported_model_params(self) -> set[StandardModelParamNames]:
+        return {
+            "temperature",
+            "top_p",
+            "top_k",
+            "max_tokens",
+            "stop_sequences",
+        }
+
     def _as_message_params(self, turns: list[Turn]) -> list["MessageParam"]:
         messages: list["MessageParam"] = []
         for turn in turns:
@@ -473,10 +497,13 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
                 },
             }
         elif isinstance(content, ContentImageRemote):
-            raise NotImplementedError(
-                "Remote images aren't supported by Anthropic (Claude). "
-                "Consider downloading the image and using content_image_file() instead."
-            )
+            return {
+                "type": "image",
+                "source": {
+                    "type": "url",
+                    "url": content.url,
+                },
+            }
         elif isinstance(content, ContentToolRequest):
             return {
                 "type": "tool_use",
@@ -490,8 +517,26 @@ class AnthropicProvider(Provider[Message, RawMessageStreamEvent, Message]):
                 "tool_use_id": content.id,
                 "is_error": content.error is not None,
             }
-            # Anthropic supports non-text contents like ImageBlockParam
-            res["content"] = content.get_model_value()  # type: ignore
+
+            if isinstance(content, ContentToolResultImage):
+                res["content"] = [
+                    {
+                        "type": "image",
+                        "source": {
+                            "type": "base64",
+                            "media_type": content.mime_type,
+                            "data": content.value,
+                        },
+                    }
+                ]
+            elif isinstance(content, ContentToolResultResource):
+                raise NotImplementedError(
+                    "ContentToolResultResource is not currently supported by Anthropic."
+                )
+            else:
+                # Anthropic supports non-text contents like ImageBlockParam
+                res["content"] = content.get_model_value()  # type: ignore
+
             return res
 
         raise ValueError(f"Unknown content type: {type(content)}")
@@ -565,7 +610,6 @@ def ChatBedrockAnthropic(
     aws_session_token: Optional[str] = None,
     base_url: Optional[str] = None,
     system_prompt: Optional[str] = None,
-    turns: Optional[list[Turn]] = None,
     kwargs: Optional["ChatBedrockClientArgs"] = None,
 ) -> Chat["SubmitInputArgs", Message]:
     """
@@ -631,13 +675,6 @@ def ChatBedrockAnthropic(
         `f"https://bedrock-runtime.{aws_region}.amazonaws.com"`.
     system_prompt
         A system prompt to set the behavior of the assistant.
-    turns
-        A list of turns to start the chat with (i.e., continuing a previous
-        conversation). If not provided, the conversation begins from scratch. Do
-        not provide non-None values for both `turns` and `system_prompt`. Each
-        message in the list should be a dictionary with at least `role` (usually
-        `system`, `user`, or `assistant`, but `tool` is also possible). Normally
-        there is also a `content` field, which is a string.
     kwargs
         Additional arguments to pass to the `anthropic.AnthropicBedrock()`
         client constructor.
@@ -711,10 +748,7 @@ def ChatBedrockAnthropic(
             base_url=base_url,
             kwargs=kwargs,
         ),
-        turns=normalize_turns(
-            turns or [],
-            system_prompt,
-        ),
+        system_prompt=system_prompt,
     )
 
 
@@ -728,10 +762,13 @@ class AnthropicBedrockProvider(AnthropicProvider):
         aws_region: str | None,
         aws_profile: str | None,
         aws_session_token: str | None,
-        max_tokens: int,
+        max_tokens: int = 4096,
         base_url: str | None,
+        name: str = "AnthropicBedrock",
         kwargs: Optional["ChatBedrockClientArgs"] = None,
     ):
+        super().__init__(name=name, model=model, max_tokens=max_tokens)
+
         try:
             from anthropic import AnthropicBedrock, AsyncAnthropicBedrock
         except ImportError:
@@ -740,9 +777,6 @@ class AnthropicBedrockProvider(AnthropicProvider):
                 "Install it with `pip install anthropic[bedrock]`."
             )
 
-        self._model = model
-        self._max_tokens = max_tokens
-
         kwargs_full: "ChatBedrockClientArgs" = {
             "aws_secret_key": aws_secret_key,
             "aws_access_key": aws_access_key,

{chatlas-0.8.1 → chatlas-0.9.1}/chatlas/_auto.py

@@ -15,7 +15,6 @@ from ._ollama import ChatOllama
 from ._openai import ChatAzureOpenAI, ChatOpenAI
 from ._perplexity import ChatPerplexity
 from ._snowflake import ChatSnowflake
-from ._turn import Turn
 
 AutoProviders = Literal[
     "anthropic",
@@ -50,7 +49,6 @@ _provider_chat_model_map: dict[AutoProviders, Callable[..., Chat]] = {
 
 def ChatAuto(
     system_prompt: Optional[str] = None,
-    turns: Optional[list[Turn]] = None,
     *,
     provider: Optional[AutoProviders] = None,
     model: Optional[str] = None,
@@ -111,6 +109,8 @@ def ChatAuto(
 
     Parameters
     ----------
+    system_prompt
+        A system prompt to set the behavior of the assistant.
     provider
         The name of the default chat provider to use. Providers are strings
         formatted in kebab-case, e.g. to use `ChatBedrockAnthropic` set
@@ -123,15 +123,6 @@ def ChatAuto(
         The name of the default model to use. This value can also be provided
         via the `CHATLAS_CHAT_MODEL` environment variable, which takes
         precedence over `model` when set.
-    system_prompt
-        A system prompt to set the behavior of the assistant.
-    turns
-        A list of turns to start the chat with (i.e., continuing a previous
-        conversation). If not provided, the conversation begins from scratch. Do
-        not provide non-`None` values for both `turns` and `system_prompt`. Each
-        message in the list should be a dictionary with at least `role` (usually
-        `system`, `user`, or `assistant`, but `tool` is also possible). Normally
-        there is also a `content` field, which is a string.
     **kwargs
         Additional keyword arguments to pass to the Chat constructor. See the
         documentation for each provider for more details on the available
@@ -169,7 +160,7 @@ def ChatAuto(
         )
 
     # `system_prompt` and `turns` always come from `ChatAuto()`
-    base_args = {"system_prompt": system_prompt, "turns": turns}
+    base_args = {"system_prompt": system_prompt}
 
     if env_model := os.environ.get("CHATLAS_CHAT_MODEL"):
         model = env_model