docs: add Pydantic AI guide + Hermes standalone provider-plugin section#72
docs: add Pydantic AI guide + Hermes standalone provider-plugin section#72MVS-source wants to merge 2 commits into
Conversation
…tion - Pydantic AI: new integration guide (AI Frameworks). Type-safe agents on Eden AI via OpenAIChatModel + OpenAIProvider; house-style env var EDEN_AI_API_KEY. - Hermes: add an optional "First-class provider plugin" section documenting the standalone model-provider plugin route (native --provider eden-ai), alongside the existing custom-provider setup. Additive edit only. Includes pydantic-ai icon SVG and docs.json nav entry. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
WalkthroughAdded a Pydantic AI integration guide and navigation entry, plus Hermes documentation for an optional Eden AI model-provider plugin and updated metadata. ChangesIntegration documentation
Estimated code review effort: 2 (Simple) | ~10 minutes Possibly related PRs
Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
The Execution Tests harness runs ```python blocks against the sandbox
API. Two docs have blocks that cannot run in the minimal test env:
- pydantic-ai.mdx: pydantic-ai is not in tests/requirements-lock.txt
- hermes.mdx: the plugin __init__.py imports Hermes' internal
`providers` module (only available inside $HERMES_HOME)
Mark them with the documented {/* skip-test */} MDX comment (invisible
in rendered docs) so CI skips execution while keeping the snippets.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@v3/integrations/pydantic-ai.mdx`:
- Around line 46-57: Update the PydanticAI example’s OpenAI configuration around
OpenAIChatModel to use the supported model/provider setup for the installed
PydanticAI version, removing the unavailable OpenAIProvider import and usage.
Preserve the Eden AI API key and base_url configuration.
- Line 158: Update the import in the pydantic-ai example to remove
ModelHTTPError and retain only the valid UnexpectedModelBehavior symbol from
pydantic_ai.exceptions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 9edec37c-039f-43bb-8b95-cd659e536fec
⛔ Files ignored due to path filters (1)
integration-logo/pydantic-ai-icondoc.svgis excluded by!**/*.svg
📒 Files selected for processing (3)
docs.jsonv3/integrations/hermes.mdxv3/integrations/pydantic-ai.mdx
| ```python Python | ||
| from pydantic_ai import Agent | ||
| from pydantic_ai.models.openai import OpenAIChatModel | ||
| from pydantic_ai.providers.openai import OpenAIProvider | ||
|
|
||
| model = OpenAIChatModel( | ||
| "openai/gpt-4o", | ||
| provider=OpenAIProvider( | ||
| api_key="YOUR_EDEN_AI_API_KEY", # Get from https://app.edenai.run | ||
| base_url="https://api.edenai.run/v3", | ||
| ), | ||
| ) |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🌐 Web query:
"OpenAIModel" OR "OpenAIChatModel" site:ai.pydantic.dev
💡 Result:
In the context of the PydanticAI framework, OpenAIChatModel is a class designed to facilitate interaction with OpenAI's API [1]. It serves as a model implementation that utilizes the official OpenAI Python client internally to manage API requests [1]. While the search results specifically identify and document OpenAIChatModel as part of the pydantic_ai.models.openai module [1], there is no distinct, documented class named OpenAIModel currently identified in the standard PydanticAI library structure; it is likely a misidentification or a conceptual reference to the base model interface or the broader family of OpenAI-compatible models [1][2]. Key characteristics of OpenAIChatModel include: - Functionality: It acts as a bridge between PydanticAI agents and OpenAI's chat-based language models [1]. - Initialization: It requires a model name (e.g., 'gpt-4o') and accepts optional parameters such as providers, model profiles, and default settings [1]. - Integration: It inherits from the base Model class [1], allowing it to be used seamlessly within PydanticAI Agents to process tasks, manage tool usage, and handle structured output [1][3][4]. If you encountered the term OpenAIModel, it may refer to the generic Model base class or a custom implementation in a specific codebase, as OpenAIChatModel is the explicit, provided implementation for OpenAI chat interfaces within the framework [1][2].
Citations:
- 1: https://ai.pydantic.dev/api/models/openai/index.md
- 2: https://ai.pydantic.dev/api/models/base/index.md
- 3: https://ai.pydantic.dev/api/agent/index.md
- 4: https://ai.pydantic.dev/examples/bank-support/index.md
🌐 Web query:
"OpenAIProvider" site:ai.pydantic.dev pydantic_ai.providers.openai
💡 Result:
In the Pydantic AI library, OpenAI support is provided through the pydantic_ai.models.openai module, which defines model classes for interacting with OpenAI APIs [1]. Specifically, there is no top-level class named OpenAIProvider; instead, models are initialized using model strings (e.g., 'openai:gpt-4o') or by instantiating OpenAIChatModel or OpenAIResponsesModel [1]. Key points regarding OpenAI integration in Pydantic AI: 1. Model Initialization: When defining an Agent, you specify the model using a string identifier [2]. For example, Agent('openai:gpt-4o') automatically configures the agent to use the OpenAI provider [3][2]. 2. Provider Classes: - OpenAIChatModel: A model that uses the standard OpenAI Chat API [1]. - OpenAIResponsesModel: A model designed for the OpenAI Responses API [1]. 3. Provider Configuration: Both model classes accept a provider argument during initialization, which defaults to 'openai' [1]. This argument allows for specifying alternative compatible providers or custom AsyncOpenAI client configurations [1]. 4. Documentation Reference: Technical details and configuration options, such as OpenAIChatModelSettings, can be found in the pydantic_ai.models.openai API documentation [1].
Citations:
- 1: https://ai.pydantic.dev/api/models/openai/index.md
- 2: https://ai.pydantic.dev/api/agent/index.md
- 3: https://ai.pydantic.dev/examples/flight-booking/index.md
🌐 Web query:
site:ai.pydantic.dev pydantic_ai.models.openai OpenAIChatModel provider api_key base_url
💡 Result:
In Pydantic AI, the OpenAIChatModel is designed to interface with the OpenAI API (or compatible services) [1]. Configuration of the api_key and base_url for OpenAIChatModel is typically handled through the underlying provider rather than directly in the OpenAIChatModel constructor [1]. 1. Provider Configuration: The OpenAIChatModel constructor accepts a provider argument [1]. By default, this is set to 'openai' [1]. To customize parameters like api_key or base_url, you should instantiate a specific provider object (e.g., OpenAIProvider or a similar provider class) and pass it to the provider argument of the OpenAIChatModel [1]. 2. Environment Variables: For standard OpenAI usage, Pydantic AI typically retrieves the API key from environment variables (e.g., OPENAI_API_KEY) automatically when using the default provider [1]. 3. General Pattern for Custom Providers: While documentation for specific OpenAIChatModel provider configuration options can vary by version, the general pattern for custom configurations in Pydantic AI involves [2][3]: - Instantiating the provider class (e.g., provider = OpenAIProvider(api_key='...', base_url='...')). - Passing this instance to the model (e.g., model = OpenAIChatModel(..., provider=provider)). If you are using a self-hosted or compatible OpenAI-like API, ensure the provider instance is configured with the correct base_url and api_key before initializing the OpenAIChatModel [1]. Check your specific version's API documentation for the exact provider class exported by pydantic_ai.providers [1][2].
Citations:
- 1: https://ai.pydantic.dev/api/models/openai/index.md
- 2: https://ai.pydantic.dev/models/openrouter/index.md
- 3: https://ai.pydantic.dev/models/xai/index.md
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect the relevant file and any nearby Pydantic AI usage in docs.
git ls-files 'v3/integrations/pydantic-ai.mdx' 'v3/**/*.mdx' | sed -n '1,80p'
echo
wc -l v3/integrations/pydantic-ai.mdx
echo
cat -n v3/integrations/pydantic-ai.mdx | sed -n '35,70p'
echo
rg -n "OpenAIChatModel|OpenAIProvider|OpenAIResponsesModel|Agent\\('openai:|pydantic_ai" v3 -g '*.mdx'Repository: edenai/docs
Length of output: 6263
🌐 Web query:
site:ai.pydantic.dev "pydantic_ai.providers.openai" OR "OpenAIProvider" OR "class OpenAIProvider"
💡 Result:
PydanticAI does not have a class named OpenAIProvider within the pydantic_ai.providers namespace. In PydanticAI, OpenAI integration is primarily handled through the pydantic_ai.models.openai module [1]. The core class for using OpenAI models is OpenAIChatModel (or OpenAIResponsesModel for the Responses API) [1]. When configuring an agent, you typically specify the model name (e.g., 'openai:gpt-5.2') directly in the Agent constructor [2][3]. Internally, the framework uses these model classes to interact with the OpenAI API. While there is a concept of a provider within the OpenAIChatModel configuration—often defaulting to 'openai' or 'gateway'—it is managed via string identifiers or specific provider objects rather than a top-level class named OpenAIProvider [1]. If you are looking to define a custom provider or configure the underlying connection, you would interact with the model settings or the specific model class constructors [1].
Citations:
- 1: https://ai.pydantic.dev/api/models/openai/index.md
- 2: https://ai.pydantic.dev/api/agent/index.md
- 3: https://ai.pydantic.dev/examples/flight-booking/index.md
Replace OpenAIProvider with the supported PydanticAI OpenAI configuration
OpenAIChatModel is valid, but pydantic_ai.providers.openai.OpenAIProvider is not exposed in PydanticAI, so this snippet will fail on import. Use the documented model/provider setup for the installed version instead.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@v3/integrations/pydantic-ai.mdx` around lines 46 - 57, Update the PydanticAI
example’s OpenAI configuration around OpenAIChatModel to use the supported
model/provider setup for the installed PydanticAI version, removing the
unavailable OpenAIProvider import and usage. Preserve the Eden AI API key and
base_url configuration.
| from pydantic_ai import Agent | ||
| from pydantic_ai.models.openai import OpenAIChatModel | ||
| from pydantic_ai.providers.openai import OpenAIProvider | ||
| from pydantic_ai.exceptions import ModelHTTPError, UnexpectedModelBehavior |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🌐 Web query:
"ModelHTTPError" site:ai.pydantic.dev
💡 Result:
ModelHTTPError is not a standard error class in the Pydantic AI framework or general Python programming. Based on the provided technical documentation for Pydantic AI, the library primarily uses UserError for configuration or usage issues [1], ModelRetry for validation failures during agent runs [2], and NotImplementedError for base model methods that have not been implemented by specific providers [1]. If you are encountering an error related to HTTP requests in Pydantic AI, it typically relates to the underlying HTTP client used by the model provider (e.g., OpenAI, Anthropic, or Groq) [3][4][5]. These are usually handled by the provider's official SDK or standard HTTP exception classes rather than a specific library-wide ModelHTTPError. If you are seeing this name, it may be a custom exception defined within your specific codebase or a third-party library not covered by the official Pydantic AI documentation.
Citations:
- 1: https://ai.pydantic.dev/api/models/base/index.md
- 2: https://ai.pydantic.dev/api/agent/index.md
- 3: https://ai.pydantic.dev/api/models/openai/index.md
- 4: https://ai.pydantic.dev/api/models/groq/
- 5: https://ai.pydantic.dev/api/models/anthropic/index.md
🌐 Web query:
site:ai.pydantic.dev "class ModelHTTPError" OR "ModelHTTPError" "pydantic_ai.exceptions"
💡 Result:
Based on the provided documentation for Pydantic AI, there is no public class named ModelHTTPError defined within the pydantic_ai.exceptions module or the broader library. Pydantic AI uses standard exception handling mechanisms, and model-related errors typically surface through specific exceptions related to request failures or configuration issues, such as UserError or general HTTP/network exceptions depending on the underlying provider client (e.g., httpx for OpenAI or Anthropic). [1][2]
Citations:
- 1: https://ai.pydantic.dev/api/models/base/index.md
- 2: https://ai.pydantic.dev/api/models/anthropic/index.md
Drop ModelHTTPError from the import. pydantic_ai.exceptions doesn’t expose that symbol, so this snippet won’t run as written.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@v3/integrations/pydantic-ai.mdx` at line 158, Update the import in the
pydantic-ai example to remove ModelHTTPError and retain only the valid
UnexpectedModelBehavior symbol from pydantic_ai.exceptions.
|
Remplacée par #75 (historique de commits nettoyé, même contenu). |
1 participant
What
OpenAIChatModel+OpenAIProvider, pointed athttps://api.edenai.run/v3.--provider eden-ai, shows up inhermes model/hermes doctor), alongside the existingcustom-provider setup.Files
v3/integrations/pydantic-ai.mdx(new)integration-logo/pydantic-ai-icondoc.svg(new, square, brand magenta)v3/integrations/hermes.mdx(edit: +1 section,dateModifiedbump — 45 insertions, no existing lines rewritten)docs.json—pydantic-aiadded to AI FrameworksConventions
<TechArticleSchema>+<CodeGroup>).EDEN_AI_API_KEY(house style) for Pydantic AI. Hermes keepsEDENAI_API_KEYsince it derives the name from the base URL host.To confirm before merge
register_provider/ProviderProfilefields) against the current Hermes plugin loader.🤖 Generated with Claude Code
Summary by CodeRabbit