first commit
This commit is contained in:
Beyhan Oğur
449
docs/integrations/anthropic-sdk/overview.mdx
Normal file
449
docs/integrations/anthropic-sdk/overview.mdx
Normal file
@@ -0,0 +1,449 @@
|
||||
---
|
||||
title: "Overview"
|
||||
description: "Use Bifrost as a drop-in replacement for Anthropic API with full compatibility and enhanced features."
|
||||
icon: "book"
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Bifrost provides complete Anthropic API compatibility through protocol adaptation. The integration handles request transformation, response normalization, and error mapping between Anthropic's Messages API specification and Bifrost's internal processing pipeline.
|
||||
|
||||
This integration enables you to utilize Bifrost's features like governance, load balancing, semantic caching, multi-provider support, and more, all while preserving your existing Anthropic SDK-based architecture.
|
||||
|
||||
**Endpoint:** `/anthropic`
|
||||
|
||||
<Note>
|
||||
**Enabling the beta header**: Anthropic frequently uses the `anthropic-beta` header to gate access to new features.
|
||||
Clients like Vercels AI SDK use these. Bifrost will block unrecognized headers by default for security purposes.
|
||||
To enable the beta header for full compatability, add `anthropic-beta` to the AllowList under Settings -> Client Settings in the UI.
|
||||
</Note>
|
||||
|
||||
---
|
||||
|
||||
## Setup
|
||||
|
||||
<Tabs group="anthropic-sdk">
|
||||
<Tab title="Python">
|
||||
|
||||
```python {5}
|
||||
import anthropic
|
||||
|
||||
# Configure client to use Bifrost
|
||||
client = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="dummy-key" # Keys handled by Bifrost
|
||||
)
|
||||
|
||||
# Make requests as usual
|
||||
response = client.messages.create(
|
||||
model="claude-3-sonnet-20240229",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello!"}]
|
||||
)
|
||||
|
||||
print(response.content[0].text)
|
||||
```
|
||||
|
||||
</Tab>
|
||||
<Tab title="JavaScript">
|
||||
|
||||
```javascript {5}
|
||||
import Anthropic from "@anthropic-ai/sdk";
|
||||
|
||||
// Configure client to use Bifrost
|
||||
const anthropic = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "dummy-key", // Keys handled by Bifrost
|
||||
});
|
||||
|
||||
// Make requests as usual
|
||||
const response = await anthropic.messages.create({
|
||||
model: "claude-3-sonnet-20240229",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello!" }],
|
||||
});
|
||||
|
||||
console.log(response.content[0].text);
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
---
|
||||
|
||||
## Provider/Model Usage Examples
|
||||
|
||||
Use multiple providers through the same Anthropic SDK format by prefixing model names with the provider:
|
||||
|
||||
<Tabs group="anthropic-sdk">
|
||||
<Tab title="Python">
|
||||
|
||||
```python
|
||||
import anthropic
|
||||
|
||||
client = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="dummy-key"
|
||||
)
|
||||
|
||||
# Anthropic models (default)
|
||||
anthropic_response = client.messages.create(
|
||||
model="claude-3-sonnet-20240229",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from Claude!"}]
|
||||
)
|
||||
|
||||
# OpenAI models via Anthropic SDK format
|
||||
openai_response = client.messages.create(
|
||||
model="openai/gpt-4o-mini",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from OpenAI!"}]
|
||||
)
|
||||
|
||||
# Google Vertex models via Anthropic SDK format
|
||||
vertex_response = client.messages.create(
|
||||
model="vertex/gemini-pro",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from Gemini!"}]
|
||||
)
|
||||
|
||||
# Azure models
|
||||
azure_response = client.messages.create(
|
||||
model="azure/gpt-4o",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from Azure!"}]
|
||||
)
|
||||
|
||||
# Local Ollama models
|
||||
ollama_response = client.messages.create(
|
||||
model="ollama/llama3.1:8b",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from Ollama!"}]
|
||||
)
|
||||
```
|
||||
|
||||
</Tab>
|
||||
<Tab title="JavaScript">
|
||||
|
||||
```javascript
|
||||
import Anthropic from "@anthropic-ai/sdk";
|
||||
|
||||
const anthropic = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "dummy-key",
|
||||
});
|
||||
|
||||
// Anthropic models (default)
|
||||
const anthropicResponse = await anthropic.messages.create({
|
||||
model: "claude-3-sonnet-20240229",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from Claude!" }],
|
||||
});
|
||||
|
||||
// OpenAI models via Anthropic SDK format
|
||||
const openaiResponse = await anthropic.messages.create({
|
||||
model: "openai/gpt-4o-mini",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from OpenAI!" }],
|
||||
});
|
||||
|
||||
// Google Vertex models via Anthropic SDK format
|
||||
const vertexResponse = await anthropic.messages.create({
|
||||
model: "vertex/gemini-pro",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from Gemini!" }],
|
||||
});
|
||||
|
||||
// Azure models
|
||||
const azureResponse = await anthropic.messages.create({
|
||||
model: "azure/gpt-4o",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from Azure!" }],
|
||||
});
|
||||
|
||||
// Local Ollama models
|
||||
const ollamaResponse = await anthropic.messages.create({
|
||||
model: "ollama/llama3.1:8b",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from Ollama!" }],
|
||||
});
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
---
|
||||
|
||||
## Adding Custom Headers
|
||||
|
||||
Pass custom headers required by Bifrost plugins (like governance, telemetry, etc.):
|
||||
|
||||
<Tabs group="anthropic-sdk">
|
||||
<Tab title="Python">
|
||||
|
||||
```python
|
||||
import anthropic
|
||||
|
||||
client = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="dummy-key",
|
||||
default_headers={
|
||||
"x-bf-vk": "vk_12345", # Virtual key for governance
|
||||
}
|
||||
)
|
||||
|
||||
response = client.messages.create(
|
||||
model="claude-3-sonnet-20240229",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello with custom headers!"}]
|
||||
)
|
||||
```
|
||||
|
||||
</Tab>
|
||||
<Tab title="JavaScript">
|
||||
|
||||
```javascript
|
||||
import Anthropic from "@anthropic-ai/sdk";
|
||||
|
||||
const anthropic = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "dummy-key",
|
||||
defaultHeaders: {
|
||||
"x-bf-vk": "vk_12345", // Virtual key for governance
|
||||
},
|
||||
});
|
||||
|
||||
const response = await anthropic.messages.create({
|
||||
model: "claude-3-sonnet-20240229",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello with custom headers!" }],
|
||||
});
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
---
|
||||
|
||||
## Using Direct Keys
|
||||
|
||||
Pass API keys directly in requests to bypass Bifrost's load balancing. You can pass any provider's API key (OpenAI, Anthropic, Mistral, etc.) since Bifrost only looks for `Authorization` or `x-api-key` headers. This requires the **Allow Direct API keys** option to be enabled in Bifrost configuration.
|
||||
|
||||
> **Learn more:** See [Key Management](../../features/keys-management#direct-key-bypass) for enabling direct API key usage.
|
||||
|
||||
<Tabs group="anthropic-sdk">
|
||||
<Tab title="Python">
|
||||
|
||||
```python
|
||||
import anthropic
|
||||
|
||||
# Using Anthropic's API key directly
|
||||
client_with_direct_key = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="sk-your-anthropic-key" # Anthropic's API key works
|
||||
)
|
||||
|
||||
anthropic_response = client_with_direct_key.messages.create(
|
||||
model="claude-3-sonnet-20240229",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello from Claude!"}]
|
||||
)
|
||||
|
||||
# or pass different provider keys per request using headers
|
||||
client = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="dummy-key"
|
||||
)
|
||||
|
||||
# Use Anthropic key for Claude
|
||||
anthropic_response = client.messages.create(
|
||||
model="claude-3-sonnet-20240229",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello Claude!"}],
|
||||
extra_headers={
|
||||
"x-api-key": "sk-ant-your-anthropic-key"
|
||||
}
|
||||
)
|
||||
|
||||
# Use OpenAI key for GPT models
|
||||
openai_response = client.messages.create(
|
||||
model="openai/gpt-4o-mini",
|
||||
max_tokens=1000,
|
||||
messages=[{"role": "user", "content": "Hello GPT!"}],
|
||||
extra_headers={
|
||||
"Authorization": "Bearer sk-your-openai-key"
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
</Tab>
|
||||
<Tab title="JavaScript">
|
||||
|
||||
```javascript
|
||||
import Anthropic from "@anthropic-ai/sdk";
|
||||
|
||||
// Using Anthropic's API key directly
|
||||
const anthropicWithDirectKey = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "sk-your-anthropic-key", // Anthropic's API key works
|
||||
});
|
||||
|
||||
|
||||
const anthropicResponse = await anthropicWithDirectKey.messages.create({
|
||||
model: "claude-3-sonnet-20240229",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello from Claude!" }],
|
||||
});
|
||||
|
||||
|
||||
// or pass different provider keys per request using headers
|
||||
const anthropic = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "dummy-key",
|
||||
});
|
||||
|
||||
// Use Anthropic key for Claude
|
||||
const anthropicResponse = await anthropic.messages.create({
|
||||
model: "claude-3-sonnet-20240229",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello Claude!" }],
|
||||
headers: {
|
||||
"x-api-key": "sk-ant-your-anthropic-key",
|
||||
},
|
||||
});
|
||||
|
||||
// Use OpenAI key for GPT models
|
||||
const openaiResponseWithHeader = await anthropic.messages.create({
|
||||
model: "openai/gpt-4o-mini",
|
||||
max_tokens: 1000,
|
||||
messages: [{ role: "user", content: "Hello GPT!" }],
|
||||
headers: {
|
||||
"Authorization": "Bearer sk-your-openai-key",
|
||||
},
|
||||
});
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
---
|
||||
|
||||
## Async Inference
|
||||
|
||||
Submit inference requests asynchronously and poll for results later using the `x-bf-async` header. This is useful for long-running requests where you don't want to hold a connection open. See [Async Inference](../../features/async-inference) for full details.
|
||||
|
||||
<Note>
|
||||
Async inference requires a [Logs Store](../../features/observability/default) to be configured and is not compatible with streaming.
|
||||
</Note>
|
||||
|
||||
### Messages
|
||||
|
||||
<Tabs group="anthropic-sdk">
|
||||
<Tab title="Python">
|
||||
|
||||
```python
|
||||
import anthropic
|
||||
import time
|
||||
|
||||
client = anthropic.Anthropic(
|
||||
base_url="http://localhost:8080/anthropic",
|
||||
api_key="dummy-key"
|
||||
)
|
||||
|
||||
# Submit async request
|
||||
initial = client.messages.create(
|
||||
model="anthropic/claude-sonnet-4-20250514",
|
||||
max_tokens=256,
|
||||
messages=[{"role": "user", "content": "Tell me a short story."}],
|
||||
extra_headers={"x-bf-async": "true"}
|
||||
)
|
||||
|
||||
# If content is present, the request completed synchronously
|
||||
if initial.content:
|
||||
print(initial.content[0].text)
|
||||
else:
|
||||
# Poll until completed
|
||||
while True:
|
||||
time.sleep(2)
|
||||
poll = client.messages.create(
|
||||
model="anthropic/claude-sonnet-4-20250514",
|
||||
max_tokens=256,
|
||||
messages=[{"role": "user", "content": "Tell me a short story."}],
|
||||
extra_headers={"x-bf-async-id": initial.id}
|
||||
)
|
||||
if poll.content:
|
||||
print(poll.content[0].text)
|
||||
break
|
||||
```
|
||||
|
||||
</Tab>
|
||||
<Tab title="JavaScript">
|
||||
|
||||
```javascript
|
||||
import Anthropic from "@anthropic-ai/sdk";
|
||||
|
||||
const anthropic = new Anthropic({
|
||||
baseURL: "http://localhost:8080/anthropic",
|
||||
apiKey: "dummy-key",
|
||||
});
|
||||
|
||||
// Submit async request
|
||||
const initial = await anthropic.messages.create(
|
||||
{
|
||||
model: "anthropic/claude-sonnet-4-20250514",
|
||||
max_tokens: 256,
|
||||
messages: [{ role: "user", content: "Tell me a short story." }],
|
||||
},
|
||||
{ headers: { "x-bf-async": "true" } }
|
||||
);
|
||||
|
||||
// If content is present, the request completed synchronously
|
||||
if (initial.content?.length > 0) {
|
||||
console.log(initial.content[0].text);
|
||||
} else {
|
||||
// Poll until completed
|
||||
while (true) {
|
||||
await new Promise((r) => setTimeout(r, 2000));
|
||||
const poll = await anthropic.messages.create(
|
||||
{
|
||||
model: "anthropic/claude-sonnet-4-20250514",
|
||||
max_tokens: 256,
|
||||
messages: [{ role: "user", content: "Tell me a short story." }],
|
||||
},
|
||||
{ headers: { "x-bf-async-id": initial.id } }
|
||||
);
|
||||
if (poll.content?.length > 0) {
|
||||
console.log(poll.content[0].text);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
### Async Headers
|
||||
|
||||
| Header | Description |
|
||||
|---|---|
|
||||
| `x-bf-async: true` | Submit the request as an async job. Returns immediately with a job ID. |
|
||||
| `x-bf-async-id: <job-id>` | Poll for results of a previously submitted async job. |
|
||||
| `x-bf-async-job-result-ttl: <seconds>` | Override the default result TTL (default: 3600s). |
|
||||
|
||||
---
|
||||
|
||||
## Supported Features
|
||||
|
||||
The Anthropic integration supports all features that are available in both the Anthropic SDK and Bifrost core functionality. If the Anthropic SDK supports a feature and Bifrost supports it, the integration will work seamlessly.
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
- **[Files and Batch API](./files-and-batch)** - File uploads and batch processing
|
||||
- **[OpenAI SDK](../openai-sdk/overview)** - GPT integration patterns
|
||||
- **[Google GenAI SDK](../genai-sdk)** - Gemini integration patterns
|
||||
- **[Configuration](../../quickstart/README)** - Bifrost setup and configuration
|
||||
- **[Core Features](../../features/)** - Advanced Bifrost capabilities
|
||||
|
||||
Reference in New Issue
Block a user