Skip to content

Commit 2618109

Browse files
Merge branch 'v1.15' into scheduler
2 parents 859e135 + 1408ba2 commit 2618109

File tree

6 files changed

+38
-39
lines changed

6 files changed

+38
-39
lines changed

daprdocs/content/en/developing-applications/debugging/bridge-to-kubernetes.md

-28
This file was deleted.

daprdocs/content/en/developing-applications/sdks/sdk-serialization.md daprdocs/content/en/developing-applications/local-development/sdk-serialization.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
---
22
type: docs
33
title: "Serialization in Dapr's SDKs"
4-
linkTitle: "Serialization"
4+
linkTitle: "SDK Serialization"
55
description: "How Dapr serializes data within the SDKs"
6-
weight: 2000
6+
weight: 400
77
aliases:
88
- '/developing-applications/sdks/serialization/'
99
---

daprdocs/content/en/operations/hosting/kubernetes/kubernetes-overview.md

-1
Original file line numberDiff line numberDiff line change
@@ -62,4 +62,3 @@ For information about:
6262
- [Upgrade Dapr on a Kubernetes cluster]({{< ref kubernetes-upgrade >}})
6363
- [Production guidelines for Dapr on Kubernetes]({{< ref kubernetes-production.md >}})
6464
- [Dapr Kubernetes Quickstart](https://github.com/dapr/quickstarts/tree/master/tutorials/hello-kubernetes)
65-
- [Use Bridge to Kubernetes to debug Dapr apps locally, while connected to your Kubernetes cluster]({{< ref bridge-to-kubernetes >}})

daprdocs/content/en/reference/api/conversation_api.md

+31-7
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ Dapr provides an API to interact with Large Language Models (LLMs) and enables c
1717
This endpoint lets you converse with LLMs.
1818

1919
```
20-
POST /v1.0-alpha1/conversation/<llm-name>/converse
20+
POST http://localhost:<daprPort>/v1.0-alpha1/conversation/<llm-name>/converse
2121
```
2222

2323
### URL parameters
@@ -30,17 +30,40 @@ POST /v1.0-alpha1/conversation/<llm-name>/converse
3030

3131
| Field | Description |
3232
| --------- | ----------- |
33-
| `conversationContext` | |
34-
| `inputs` | |
35-
| `parameters` | |
33+
| `conversationContext` | The ID of an existing chat room (like in ChatGPT). |
34+
| `inputs` | Inputs for the conversation. Multiple inputs at one time are supported. |
35+
| `metadata` | [Metadata](#metadata) passed to conversation components. |
3636

37+
#### Metadata
38+
39+
Metadata can be sent in the request’s URL. It must be prefixed with `metadata.`, as shown in the table below.
40+
41+
| Parameter | Description |
42+
| --------- | ----------- |
43+
| `metadata.key` | The API key for the component. `key` is not applicable to the [AWS Bedrock component]({{< ref "aws-bedrock.md#authenticating-aws" >}}). |
44+
| `metadata.model` | The Large Language Model you're using. Value depends on which conversation component you're using. `model` is not applicable to the [DeepSeek component]({{< ref deepseek.md >}}). |
45+
| `metadata.cacheTTL` | A time-to-live value for a prompt cache to expire. Uses Golang duration format. |
46+
47+
For example, to call for [Anthropic]({{< ref anthropic.md >}}):
48+
49+
```bash
50+
curl POST http://localhost:3500/v1.0-alpha1/conversation/anthropic/converse?metadata.key=key1&metadata.model=claude-3-5-sonnet-20240620&metadata.cacheTTL=10m
51+
```
52+
53+
{{% alert title="Note" color="primary" %}}
54+
The metadata parameters available depend on the conversation component you use. [See all the supported components for the conversation API.]({{< ref supported-conversation >}})
55+
{{% /alert %}}
3756

3857
### Request content
3958

4059
```json
4160
REQUEST = {
4261
"inputs": ["what is Dapr", "Why use Dapr"],
43-
"parameters": {},
62+
"metadata": {
63+
"model": "model-type-based-on-component-used",
64+
"key": "authKey",
65+
"cacheTTL": "10m",
66+
}
4467
}
4568
```
4669

@@ -50,7 +73,7 @@ Code | Description
5073
---- | -----------
5174
`202` | Accepted
5275
`400` | Request was malformed
53-
`500` | Request formatted correctly, error in dapr code or underlying component
76+
`500` | Request formatted correctly, error in Dapr code or underlying component
5477

5578
### Response content
5679

@@ -71,4 +94,5 @@ RESPONSE = {
7194

7295
## Next steps
7396

74-
[Conversation API overview]({{< ref conversation-overview.md >}})
97+
- [Conversation API overview]({{< ref conversation-overview.md >}})
98+
- [Supported conversation components]({{< ref supported-conversation >}})

daprdocs/content/en/reference/components-reference/supported-conversation/aws-bedrock.md

+4
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,10 @@ The above example uses secrets as plain strings. It is recommended to use a secr
3737
| `model` | N | The LLM to use. Defaults to Bedrock's default provider model from Amazon. | `amazon.titan-text-express-v1` |
3838
| `cacheTTL` | N | A time-to-live value for a prompt cache to expire. Uses Golang duration format. | `10m` |
3939

40+
## Authenticating AWS
41+
42+
Instead of using a `key` parameter, AWS Bedrock authenticates using Dapr's standard method of IAM or static credentials. [Learn more about authenticating with AWS.]({{< ref authenticating-aws.md >}})
43+
4044
## Related links
4145

4246
- [Conversation API overview]({{< ref conversation-overview.md >}})

daprdocs/content/en/reference/components-reference/supported-conversation/deepseek.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ The above example uses secrets as plain strings. It is recommended to use a secr
3232
| Field | Required | Details | Example |
3333
|--------------------|:--------:|---------|---------|
3434
| `key` | Y | API key for DeepSeek. | `mykey` |
35-
| `maxToken` | N | The max amount of tokens for each request. | `2048` |
35+
| `maxTokens` | N | The max amount of tokens for each request. | `2048` |
3636

3737
## Related links
3838

0 commit comments

Comments
 (0)