XaiModel with tests and stock analysis agent #3400
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,7 @@ | ||
| # `pydantic_ai.models.xai` | ||
|
|
||
| ## Setup | ||
|
|
||
| For details on how to set up authentication with this model, see [model configuration for xAI](../../models/xai.md). | ||
|
|
||
| ::: pydantic_ai.models.xai |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,53 @@ | ||
| Example of using xAI's server-side web_search tool for stock analysis. | ||
|
|
||
| This example demonstrates: | ||
|
|
||
| - Using server-side tools with `XaiModel` | ||
| - Structured output with Agent | ||
| - Streaming responses | ||
| - Usage tracking with logfire | ||
| - Using built-in and local tools to perform a stock analysis workflow | ||
|
|
||
| In this scenario, the agent uses built-in server-side tools like web_search along with local tools to find the hottest performing stock from yesterday on NASDAQ, retrieve its current price, and provide a brief buy analysis. | ||
|
|
||
| ## Running the Example | ||
|
|
||
| With [dependencies installed and environment variables set](./setup.md#usage), run: | ||
|
|
||
| ```bash | ||
| uv run python -m pydantic_ai_examples.stock_analysis | ||
| ``` | ||
|
|
||
| Note: Requires `XAI_API_KEY` environment variable for xAI API access. | ||
|
|
||
| ## Example Output | ||
|
|
||
| ``` | ||
| 🔍 Starting stock analysis... | ||
|
|
||
| Query: What was the hottest performing stock on NASDAQ yesterday? | ||
|
|
||
| 🔧 Server-side tool: web_search | ||
|
|
||
| 🔧 Server-side tool: browse_page | ||
|
|
||
| ✅ Analysis complete! | ||
|
|
||
| 📊 Top Stock: ATGL | ||
|
|
||
| 💰 Current Price: $20.00 | ||
|
|
||
| 📈 Buy Analysis: | ||
| ATGL surged 139.84% on November 18, 2025, making it the hottest performer on NASDAQ, but pulled back 7.45% today to $20.00. The extreme volatility suggests high risk; without clear fundamental drivers, it's not recommended as a buy for most investors. Suitable only for speculative short-term trades. | ||
|
|
||
| 📊 Usage Statistics: | ||
| Requests: 1 | ||
| Input Tokens: 19150 | ||
| Output Tokens: 526 | ||
| Total Tokens: 19676 | ||
| Server-Side Tools: 7 | ||
| ``` | ||
|
|
||
| ## Example Code | ||
|
|
||
| ```snippet {path="/examples/pydantic_ai_examples/stock_analysis.py"}``` |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,73 @@ | ||
| # xAI | ||
|
|
||
| ## Install | ||
|
|
||
| To use [`XaiModel`][pydantic_ai.models.xai.XaiModel], you need to either install `pydantic-ai`, or install `pydantic-ai-slim` with the `xai` optional group: | ||
|
|
||
| ```bash | ||
| pip/uv-add "pydantic-ai-slim[xai]" | ||
| ``` | ||
|
|
||
| ## Configuration | ||
|
|
||
| To use xAI models from [xAI](https://x.ai/api) through their API, go to [console.x.ai](https://console.x.ai/team/default/api-keys) to create an API key. | ||
|
|
||
| [docs.x.ai][https://docs.x.ai/docs/models] contains a list of available xAI models. | ||
|
|
||
| ## Environment variable | ||
|
|
||
| Once you have the API key, you can set it as an environment variable: | ||
|
|
||
| ```bash | ||
| export XAI_API_KEY='your-api-key' | ||
| ``` | ||
|
|
||
| You can then use [`XaiModel`][pydantic_ai.models.xai.XaiModel] by name: | ||
|
|
||
| ```python | ||
| from pydantic_ai import Agent | ||
|
|
||
| agent = Agent('xai:grok-4-1-fast-non-reasoning') | ||
| ... | ||
| ``` | ||
|
|
||
| Or initialise the model directly: | ||
|
|
||
| ```python | ||
| from pydantic_ai import Agent | ||
| from pydantic_ai.models.xai import XaiModel | ||
|
|
||
| # Uses XAI_API_KEY environment variable | ||
| model = XaiModel('grok-4-1-fast-non-reasoning') | ||
| agent = Agent(model) | ||
| ... | ||
| ``` | ||
|
|
||
| You can also customize the [`XaiModel`][pydantic_ai.models.xai.XaiModel] with a custom provider: | ||
|
|
||
| ```python | ||
| from pydantic_ai import Agent | ||
| from pydantic_ai.models.xai import XaiModel | ||
| from pydantic_ai.providers.xai import XaiProvider | ||
|
|
||
| # Custom API key | ||
| provider = XaiProvider(api_key='your-api-key') | ||
| model = XaiModel('grok-4-1-fast-non-reasoning', provider=provider) | ||
| agent = Agent(model) | ||
| ... | ||
| ``` | ||
|
|
||
| Or with a custom `xai_sdk.AsyncClient`: | ||
|
|
||
| ```python | ||
| from xai_sdk import AsyncClient | ||
| from pydantic_ai import Agent | ||
| from pydantic_ai.models.xai import XaiModel | ||
| from pydantic_ai.providers.xai import XaiProvider | ||
|
|
||
| xai_client = AsyncClient(api_key='your-api-key') | ||
| provider = XaiProvider(xai_client=xai_client) | ||
| model = XaiModel('grok-4-1-fast-non-reasoning', provider=provider) | ||
| agent = Agent(model) | ||
| ... | ||
| ``` |
brightsparc marked this conversation as resolved.
Show resolved
Hide resolved
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,106 @@ | ||
| """Example of using Grok's server-side web_search tool. | ||
|
|
||
| This agent: | ||
| 1. Uses web_search to find the hottest performing stock yesterday | ||
| 2. Provides buy analysis for the user | ||
| """ | ||
|
|
||
| import logfire | ||
| from pydantic import BaseModel, Field | ||
|
|
||
| from pydantic_ai import ( | ||
| Agent, | ||
| BuiltinToolCallPart, | ||
| RunContext, | ||
| WebSearchTool, | ||
| ) | ||
| from pydantic_ai.models.xai import XaiModel | ||
|
|
||
| logfire.configure() | ||
| logfire.instrument_pydantic_ai() | ||
|
|
||
| # Configure for xAI API - XAI_API_KEY environment variable is required | ||
| # The model will automatically use XaiProvider with the API key from the environment | ||
|
|
||
| # Create the model using XaiModel with server-side tools | ||
| model = XaiModel('grok-4-1-fast-non-reasoning') | ||
|
|
||
|
|
||
| class StockAnalysis(BaseModel): | ||
| """Analysis of top performing stock.""" | ||
|
|
||
| stock_symbol: str = Field(description='Stock ticker symbol') | ||
| performance_change: float = Field( | ||
| description="Yesterday's performance change percentage" | ||
| ) | ||
| current_price: float = Field(description='Current stock price') | ||
| buy_analysis: str = Field(description='Brief analysis for whether to buy the stock') | ||
|
|
||
|
|
||
| # This agent uses server-side web search to research stocks | ||
| stock_analysis_agent = Agent[None, StockAnalysis]( | ||
| model=model, | ||
| output_type=StockAnalysis, | ||
| builtin_tools=[WebSearchTool()], | ||
| system_prompt=( | ||
| 'You are a stock analysis assistant. ' | ||
| 'First, use web_search to find the hottest performing stock from yesterday on NASDAQ, including its symbol and performance change. ' | ||
| 'Then, use the local get_current_price tool to get its current price. ' | ||
| 'Finally, provide a brief buy analysis explaining whether this is a good buy.' | ||
| ), | ||
| ) | ||
|
|
||
|
|
||
| @stock_analysis_agent.tool | ||
| def get_current_price(ctx: RunContext, symbol: str) -> float: | ||
| """Get the current price for a stock symbol from local database.""" | ||
| # Simulate local database lookup | ||
| price_db = { | ||
| 'ATGL': 20.00, | ||
| 'EXAMPLE': 150.00, | ||
| # Add more as needed | ||
| } | ||
| return price_db.get(symbol, 0.0) # Return 0 if not found | ||
|
|
||
|
|
||
| async def main(): | ||
| """Run the stock analysis agent.""" | ||
| query = 'What was the hottest performing stock on NASDAQ yesterday?' | ||
|
|
||
| print('🔍 Starting stock analysis...\n') | ||
| print(f'Query: {query}\n') | ||
|
|
||
| async with stock_analysis_agent.run_stream(query) as result: | ||
| # Stream responses as they happen | ||
| async for message, _is_last in result.stream_responses(): | ||
| for part in message.parts: | ||
| if isinstance(part, BuiltinToolCallPart): | ||
| print(f'🔧 Server-side tool: {part.tool_name}') | ||
|
|
||
| # Access output after streaming is complete | ||
| output = await result.get_output() | ||
|
|
||
| print('\n✅ Analysis complete!\n') | ||
|
|
||
| print(f'📊 Top Stock: {output.stock_symbol}') | ||
| print(f'📈 Performance Change: {output.performance_change}%') | ||
| print(f'💰 Current Price: ${output.current_price:.2f}') | ||
| print(f'\n📊 Buy Analysis:\n{output.buy_analysis}') | ||
|
|
||
| # Show usage statistics | ||
| usage = result.usage() | ||
| print('\n📊 Usage Statistics:') | ||
| print(f' Requests: {usage.requests}') | ||
| print(f' Input Tokens: {usage.input_tokens}') | ||
| print(f' Output Tokens: {usage.output_tokens}') | ||
| print(f' Total Tokens: {usage.total_tokens}') | ||
|
|
||
| # Show server-side tools usage if available | ||
| if usage.details and 'server_side_tools_used' in usage.details: | ||
| print(f' Server-Side Tools: {usage.details["server_side_tools_used"]}') | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| import asyncio | ||
|
|
||
| asyncio.run(main()) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's remove this example