pydantic-ai 1.0.8__py3-none-any.whl → 1.14.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. README.md +4 -4
  2. {pydantic_ai-1.0.8.dist-info → pydantic_ai-1.14.0.dist-info}/METADATA +20 -9
  3. pydantic_ai-1.14.0.dist-info/RECORD +6 -0
  4. pydantic_ai-1.0.8.dist-info/RECORD +0 -6
  5. {pydantic_ai-1.0.8.dist-info → pydantic_ai-1.14.0.dist-info}/WHEEL +0 -0
  6. {pydantic_ai-1.0.8.dist-info → pydantic_ai-1.14.0.dist-info}/entry_points.txt +0 -0
  7. {pydantic_ai-1.0.8.dist-info → pydantic_ai-1.14.0.dist-info}/licenses/LICENSE +0 -0
README.md CHANGED
@@ -39,7 +39,7 @@ We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI
39
39
  [Pydantic Validation](https://docs.pydantic.dev/latest/) is the validation layer of the OpenAI SDK, the Google ADK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more. _Why use the derivative when you can go straight to the source?_ :smiley:
40
40
 
41
41
  2. **Model-agnostic**:
42
- Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
42
+ Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius, OVHcloud, and Outlines. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
43
43
 
44
44
  3. **Seamless Observability**:
45
45
  Tightly [integrates](https://ai.pydantic.dev/logfire) with [Pydantic Logfire](https://pydantic.dev/logfire), our general-purpose OpenTelemetry observability platform, for real-time debugging, evals-based performance monitoring, and behavior, tracing, and cost tracking. If you already have an observability platform that supports OTel, you can [use that too](https://ai.pydantic.dev/logfire#alternative-observability-backends).
@@ -50,14 +50,14 @@ Designed to give your IDE or AI coding agent as much context as possible for aut
50
50
  5. **Powerful Evals**:
51
51
  Enables you to systematically test and [evaluate](https://ai.pydantic.dev/evals) the performance and accuracy of the agentic systems you build, and monitor the performance over time in Pydantic Logfire.
52
52
 
53
- 6. **MCP, A2A, and AG-UI**:
54
- Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/client), [Agent2Agent](https://ai.pydantic.dev/a2a), and [AG-UI](https://ai.pydantic.dev/ag-ui) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
53
+ 6. **MCP, A2A, and UI**:
54
+ Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/overview), [Agent2Agent](https://ai.pydantic.dev/a2a), and various [UI event stream](https://ai.pydantic.dev/ui/overview) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
55
55
 
56
56
  7. **Human-in-the-Loop Tool Approval**:
57
57
  Easily lets you flag that certain tool calls [require approval](https://ai.pydantic.dev/deferred-tools#human-in-the-loop-tool-approval) before they can proceed, possibly depending on tool call arguments, conversation history, or user preferences.
58
58
 
59
59
  8. **Durable Execution**:
60
- Enables you to build [durable agents](https://ai.pydantic.dev/temporal) that can preserve their progress across transient API failures and application errors or restarts, and handle long-running, asynchronous, and human-in-the-loop workflows with production-grade reliability.
60
+ Enables you to build [durable agents](https://ai.pydantic.dev/durable_execution/overview/) that can preserve their progress across transient API failures and application errors or restarts, and handle long-running, asynchronous, and human-in-the-loop workflows with production-grade reliability.
61
61
 
62
62
  9. **Streamed Outputs**:
63
63
  Provides the ability to [stream](https://ai.pydantic.dev/output#streamed-results) structured output continuously, with immediate validation, ensuring real time access to generated data.
{pydantic_ai-1.0.8.dist-info → pydantic_ai-1.14.0.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: pydantic-ai
3
- Version: 1.0.8
3
+ Version: 1.14.0
4
4
  Summary: Agent Framework / shim to use Pydantic with LLMs
5
5
  Project-URL: Homepage, https://ai.pydantic.dev
6
6
  Project-URL: Source, https://github.com/pydantic/pydantic-ai
@@ -14,7 +14,6 @@ Classifier: Framework :: Pydantic
14
14
  Classifier: Framework :: Pydantic :: 2
15
15
  Classifier: Intended Audience :: Developers
16
16
  Classifier: Intended Audience :: Information Technology
17
- Classifier: License :: OSI Approved :: MIT License
18
17
  Classifier: Operating System :: OS Independent
19
18
  Classifier: Programming Language :: Python
20
19
  Classifier: Programming Language :: Python :: 3
@@ -27,13 +26,25 @@ Classifier: Topic :: Internet
27
26
  Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
28
27
  Classifier: Topic :: Software Development :: Libraries :: Python Modules
29
28
  Requires-Python: >=3.10
30
- Requires-Dist: pydantic-ai-slim[ag-ui,anthropic,bedrock,cli,cohere,evals,google,groq,huggingface,logfire,mcp,mistral,openai,retries,temporal,vertexai]==1.0.8
29
+ Requires-Dist: pydantic-ai-slim[ag-ui,anthropic,bedrock,cli,cohere,evals,fastmcp,google,groq,huggingface,logfire,mcp,mistral,openai,retries,temporal,ui,vertexai]==1.14.0
31
30
  Provides-Extra: a2a
32
31
  Requires-Dist: fasta2a>=0.4.1; extra == 'a2a'
33
32
  Provides-Extra: dbos
34
- Requires-Dist: pydantic-ai-slim[dbos]==1.0.8; extra == 'dbos'
33
+ Requires-Dist: pydantic-ai-slim[dbos]==1.14.0; extra == 'dbos'
35
34
  Provides-Extra: examples
36
- Requires-Dist: pydantic-ai-examples==1.0.8; extra == 'examples'
35
+ Requires-Dist: pydantic-ai-examples==1.14.0; extra == 'examples'
36
+ Provides-Extra: outlines-llamacpp
37
+ Requires-Dist: pydantic-ai-slim[outlines-llamacpp]==1.14.0; extra == 'outlines-llamacpp'
38
+ Provides-Extra: outlines-mlxlm
39
+ Requires-Dist: pydantic-ai-slim[outlines-mlxlm]==1.14.0; extra == 'outlines-mlxlm'
40
+ Provides-Extra: outlines-sglang
41
+ Requires-Dist: pydantic-ai-slim[outlines-sglang]==1.14.0; extra == 'outlines-sglang'
42
+ Provides-Extra: outlines-transformers
43
+ Requires-Dist: pydantic-ai-slim[outlines-transformers]==1.14.0; extra == 'outlines-transformers'
44
+ Provides-Extra: outlines-vllm-offline
45
+ Requires-Dist: pydantic-ai-slim[outlines-vllm-offline]==1.14.0; extra == 'outlines-vllm-offline'
46
+ Provides-Extra: prefect
47
+ Requires-Dist: pydantic-ai-slim[prefect]==1.14.0; extra == 'prefect'
37
48
  Description-Content-Type: text/markdown
38
49
 
39
50
  <div align="center">
@@ -77,7 +88,7 @@ We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI
77
88
  [Pydantic Validation](https://docs.pydantic.dev/latest/) is the validation layer of the OpenAI SDK, the Google ADK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more. _Why use the derivative when you can go straight to the source?_ :smiley:
78
89
 
79
90
  2. **Model-agnostic**:
80
- Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
91
+ Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius, OVHcloud, and Outlines. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
81
92
 
82
93
  3. **Seamless Observability**:
83
94
  Tightly [integrates](https://ai.pydantic.dev/logfire) with [Pydantic Logfire](https://pydantic.dev/logfire), our general-purpose OpenTelemetry observability platform, for real-time debugging, evals-based performance monitoring, and behavior, tracing, and cost tracking. If you already have an observability platform that supports OTel, you can [use that too](https://ai.pydantic.dev/logfire#alternative-observability-backends).
@@ -88,14 +99,14 @@ Designed to give your IDE or AI coding agent as much context as possible for aut
88
99
  5. **Powerful Evals**:
89
100
  Enables you to systematically test and [evaluate](https://ai.pydantic.dev/evals) the performance and accuracy of the agentic systems you build, and monitor the performance over time in Pydantic Logfire.
90
101
 
91
- 6. **MCP, A2A, and AG-UI**:
92
- Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/client), [Agent2Agent](https://ai.pydantic.dev/a2a), and [AG-UI](https://ai.pydantic.dev/ag-ui) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
102
+ 6. **MCP, A2A, and UI**:
103
+ Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/overview), [Agent2Agent](https://ai.pydantic.dev/a2a), and various [UI event stream](https://ai.pydantic.dev/ui/overview) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
93
104
 
94
105
  7. **Human-in-the-Loop Tool Approval**:
95
106
  Easily lets you flag that certain tool calls [require approval](https://ai.pydantic.dev/deferred-tools#human-in-the-loop-tool-approval) before they can proceed, possibly depending on tool call arguments, conversation history, or user preferences.
96
107
 
97
108
  8. **Durable Execution**:
98
- Enables you to build [durable agents](https://ai.pydantic.dev/temporal) that can preserve their progress across transient API failures and application errors or restarts, and handle long-running, asynchronous, and human-in-the-loop workflows with production-grade reliability.
109
+ Enables you to build [durable agents](https://ai.pydantic.dev/durable_execution/overview/) that can preserve their progress across transient API failures and application errors or restarts, and handle long-running, asynchronous, and human-in-the-loop workflows with production-grade reliability.
99
110
 
100
111
  9. **Streamed Outputs**:
101
112
  Provides the ability to [stream](https://ai.pydantic.dev/output#streamed-results) structured output continuously, with immediate validation, ensuring real time access to generated data.
pydantic_ai-1.14.0.dist-info/RECORD ADDED
@@ -0,0 +1,6 @@
1
+ README.md,sha256=uZJ_xRYVOBA2ggClS_dJrrI2_tOxPtHI7hHGBLAOb-A,11639
2
+ pydantic_ai-1.14.0.dist-info/METADATA,sha256=jT6Zf0_xe_vEsYBmaQ1L-ad68QPm-zav0bHw-7avlXI,14222
3
+ pydantic_ai-1.14.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
4
+ pydantic_ai-1.14.0.dist-info/entry_points.txt,sha256=kbKxe2VtDCYS06hsI7P3uZGxcVC08-FPt1rxeiMpIps,50
5
+ pydantic_ai-1.14.0.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
6
+ pydantic_ai-1.14.0.dist-info/RECORD,,
pydantic_ai-1.0.8.dist-info/RECORD DELETED
@@ -1,6 +0,0 @@
1
- README.md,sha256=t2tWkJDwzT_98YeJIS9C4RWpl-Tt_Zu-geAgwkGslA8,11565
2
- pydantic_ai-1.0.8.dist-info/METADATA,sha256=i-A7hhMv9wd5hU3n_YShQ87VAZ3VKEbJUdgyG5pgRUU,13467
3
- pydantic_ai-1.0.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
4
- pydantic_ai-1.0.8.dist-info/entry_points.txt,sha256=kbKxe2VtDCYS06hsI7P3uZGxcVC08-FPt1rxeiMpIps,50
5
- pydantic_ai-1.0.8.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
6
- pydantic_ai-1.0.8.dist-info/RECORD,,