|
28 | 28 | </CalloutBox> |
29 | 29 | </Section> |
30 | 30 |
|
31 | | - <Section Heading="What is the AWS Bedrock Converse API and Why Use It?" Level="4"> |
32 | | - <p> |
33 | | - As generative AI becomes more integrated into business workflows, the need for natural, multi-turn conversations with AI models is growing. AWS Bedrock's <b>Converse API</b> is designed to simplify these interactions, enabling developers to build chatbots, virtual agents, and assistants that can maintain context and handle complex dialogues. |
34 | | - </p> |
35 | | - <p> |
36 | | - Unlike the traditional <b>Invoke API</b>, which is optimized for single-turn prompts, the Converse API is purpose-built for multi-turn, stateful conversations. This makes it ideal for scenarios where the AI needs to remember previous exchanges and provide contextually relevant responses. |
37 | | - </p> |
38 | | - </Section> |
39 | | - |
40 | | - <Section Heading="What is the AWS Bedrock Converse API?" Level="4"> |
| 31 | + <Section Heading="What is the AWS Bedrock Converse API?" Level="4"> |
41 | 32 | <p> |
42 | 33 | The <b>Converse API</b> is AWS Bedrock’s answer to the growing demand for natural, multi-turn, context-aware conversations with generative AI models. As businesses and developers began integrating AI into customer support, virtual assistants, and workflow automation, it became clear that single-turn, stateless APIs (like the original <b>Invoke API</b>) were not enough. Users expect AI to remember context, follow up on previous questions, and provide a seamless, human-like experience. |
43 | 34 | </p> |
|
51 | 42 | </CalloutBox> |
52 | 43 | </Section> |
53 | 44 |
|
54 | | - <Section Heading="Why: The Need for the Converse API" Level="4"> |
55 | | - <ul> |
56 | | - <li><b>Context Retention:</b> Converse API allows the model to maintain conversation history, enabling more natural and coherent interactions.</li> |
57 | | - <li><b>Multi-Turn Dialogues:</b> Essential for customer support, virtual assistants, and any use case where back-and-forth is required.</li> |
58 | | - <li><b>Seamless Integration:</b> The API is designed to work smoothly with AWS SDKs, making it easy to add to your .NET applications.</li> |
59 | | - </ul> |
60 | | - <p> |
61 | | - In short, if your application needs to "remember" what was said earlier and respond accordingly, the Converse API is the right tool. |
62 | | - </p> |
63 | | - </Section> |
64 | | - |
65 | | - <Section Heading="Why Did AWS Create the Converse API?" Level="4"> |
| 45 | + <Section Heading="Why Did AWS Create the Converse API?" Level="4"> |
66 | 46 | <ul> |
67 | 47 | <li><b>Context Retention:</b> Real conversations require memory. Converse API lets you pass the full message history, so the model can reference earlier turns and maintain continuity.</li> |
68 | 48 | <li><b>Multi-Turn Dialogues:</b> Many business scenarios (support, sales, onboarding) require back-and-forth exchanges, not just one-off answers.</li> |
|
74 | 54 | </p> |
75 | 55 | </Section> |
76 | 56 |
|
77 | | - <Section Heading="When to Use Converse API: Use Case Scenarios" Level="4"> |
78 | | - <ul> |
79 | | - <li>AI-powered customer support agents that handle multi-step troubleshooting.</li> |
80 | | - <li>Virtual assistants that help users complete tasks over several messages.</li> |
81 | | - <li>Educational bots that guide users through learning modules.</li> |
82 | | - <li>Any scenario where context and continuity are critical for user experience.</li> |
83 | | - </ul> |
84 | | - </Section> |
85 | | - |
86 | | - <Section Heading="When and Where to Use the Converse API" Level="4"> |
| 57 | + <Section Heading="When and Where to Use the Converse API" Level="4"> |
87 | 58 | <ul> |
88 | 59 | <li><b>Customer Support:</b> Multi-step troubleshooting, order tracking, and escalation flows.</li> |
89 | 60 | <li><b>Virtual Assistants:</b> Scheduling, reminders, and task management that require context.</li> |
|
97 | 68 | </CalloutBox> |
98 | 69 | </Section> |
99 | 70 |
|
100 | | - <Section Heading="How Does Converse API Compare to Invoke API?" Level="4"> |
101 | | - <ul> |
102 | | - <li><b>Invoke API:</b> Best for single-turn, stateless prompts. Each request is independent, and the model does not retain any memory of previous interactions.</li> |
103 | | - <li><b>Converse API:</b> Designed for multi-turn, stateful conversations. The model receives the full conversation history and can generate responses that reference earlier messages.</li> |
104 | | - </ul> |
105 | | - <p> |
106 | | - If you need chat-like, context-aware interactions, use Converse. For simple, one-off completions, use Invoke. |
107 | | - </p> |
108 | | - </Section> |
109 | | - |
110 | | - <Section Heading="Converse API vs. Invoke API: Technical and Practical Differences" Level="4"> |
| 71 | + <Section Heading="Converse API vs. Invoke API: Technical and Practical Differences" Level="4"> |
111 | 72 | <ul> |
112 | 73 | <li><b>Invoke API:</b> Stateless. Each request is a single prompt/response. No memory of previous turns. Simpler, but limited for conversations.</li> |
113 | 74 | <li><b>Converse API:</b> Stateful. You send the full conversation history (as a list of messages). The model can reference, summarize, or clarify based on prior turns.</li> |
@@ -292,5 +253,9 @@ public class BedrockCustomerSupportService |
292 | 253 | </ul> |
293 | 254 | </Section> |
294 | 255 |
|
| 256 | + <CalloutBox Type="info" Title="🚀 Next in the Series"> |
| 257 | + <p>Converse API is powerful for conversations, but what if you need guaranteed structured output? Check out <a href="/blog/ai/bedrock/converse-tools">AWS Bedrock with .NET: Converse API with Tools</a> to enforce schemas and extract data reliably.</p> |
| 258 | + </CalloutBox> |
| 259 | + |
295 | 260 | <EndNotes RepositoryLink="https://github.com/ajaysskumar/ai-playground/blob/main/AwsBedrockExamples/Services/BedrockCustomerSupportService.cs" /> |
296 | 261 | </BlogContainer> |
0 commit comments