You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
**Expanded Voice Compatibility with Realtime Models**: You can use the voices ash, ballad, coral, sage, and verse with any realtime models, giving you more flexibility in voice synthesis options.
2
+
3
+
**Access to New OpenAI Models**:
4
+
You can now specify the new models `gpt-4o-realtime-preview-2024-12-17` and `gpt-4o-mini-realtime-preview-2024-12-17` when configuring `OpenAIModel.model` and `OpenAIModel.fallbackModels`.
5
+
6
+
**New ElevenLabs Voice Models Available**:
7
+
The new voice models `eleven_flash_v2` and `eleven_flash_v2_5` are now available for use in `ElevenLabsVoice` and `FallbackElevenLabsVoice`, offering potential improvements in voice performance.
You can now configure assistants to use Azure's speech transcription service by setting
3
+
`AzureSpeechTranscriber.provider` to `azure`. Additionally, you will receive azure transcriber errors like `pipeline-error-azure-speech-transcriber-failed` in `Call.endReason`, `ServerMessageEndOfCallReport.endReason`, and `ServerMessageStatusUpdate.endReason`.
4
+
5
+
2.**Combined `serverUrl` and `serverUrlSecret` into `server` Property**:
6
+
The `serverUrl` and `serverUrlSecret` properties have been replaced by a new `server` property in multiple schemas. This lets you configure webhook endpoints using the `server` object, allowing for more detailed and flexible setup, including URL and authentication, in a single place. These schemas include:
7
+
- ByoPhoneNumber
8
+
- BuyPhoneNumberDTO
9
+
- CreateByoPhoneNumberDTO
10
+
- CreateOrgDTO
11
+
- CreateTwilioPhoneNumberDTO
12
+
- CreateVapiPhoneNumberDTO
13
+
- CreateVonagePhoneNumberDTO
14
+
- ImportTwilioPhoneNumberDTO
15
+
- ImportVonagePhoneNumberDTO
16
+
- Org
17
+
- OrgWithOrgUser
18
+
- TwilioPhoneNumber
19
+
- UpdateOrgDTO
20
+
- UpdatePhoneNumberDTO
21
+
- VapiPhoneNumber
22
+
- VonagePhoneNumber
23
+
24
+
3.**Introduction of New OpenAI Models**:
25
+
You can now use `o1-preview`, `o1-preview-2024-09-12`, `o1-mini`, and `o1-mini-2024-09-12`. in `OpenAIModel.model`.
26
+
27
+
4.**Introduction of *'sonic' Voice Models* in Voice Schemas:**
28
+
You can now use `sonic` and `sonic-preview` models in `CartesiaVoice.model` and `FallbackCartesiaVoice.model` configurations.
29
+
30
+
5.**Removal of Deprecated *GroqModel* Models:**
31
+
The models `llama3-groq-8b-8192-tool-use-preview` and `llama3-groq-70b-8192-tool-use-preview` have been removed from `GroqModel.model`. You should switch to supported models to avoid any disruptions.
1.**New Transfer Plan Mode Added**: You can now include call summaries in the SIP header during blind transfers without assistant involvement with `blind-transfer-add-summary-to-sip-header` (a new `TransferPlan.mode` option). Doing so will make `ServerMessageStatusUpdate` include a `summary` when the call status is `forwarding` - which means you can access call summaries for real-time display or logging purposes in your SIP calls.
2
+
3
+
2.**Azure Speech Transcription Support**: You can now specify a new property called `AzureSpeechTranscriber.language` in Azure's Speech-to-Text service to improve the accuracy of processing spoken input.
4
+
5
+
3.**New Groq Model Available**: You can now use `'llama-3.3-70b-versatile'` in `GroqModel.model`.
subtitle: Use existing chunks/vectors from [Trieve](https://trieve.ai)
4
+
slug: customization/bring-your-own-vectors/trieve
5
+
---
6
+
7
+
Vapi supports Trieve as a knowledgebase provider, allowing you to leverage your existing document embeddings and chunks. While Vapi maintains its own storage of documents and vectors, you can seamlessly integrate with your Trieve datasets.
8
+
9
+
## Use Cases
10
+
11
+
### Existing Knowledge Base Migration
12
+
13
+
If you've already invested time in building and organizing your knowledge base in Trieve, you can continue using those vectors without having to reprocess your documents. This is particularly useful for:
14
+
15
+
- Large document collections that took significant time to process
16
+
- Carefully curated and cleaned datasets
17
+
- Custom-chunked documents with specific segmentation rules
18
+
19
+
### Parallel Systems
20
+
21
+
You might want to use both Trieve's native interface and Vapi simultaneously:
22
+
23
+
- Use Trieve's UI for content management and organization
24
+
- Leverage Vapi's chat interface and API capabilities
25
+
- Maintain consistency across both platforms
26
+
27
+
## Integration Steps
28
+
29
+
1.**Configure Trieve Credentials**
30
+
31
+
- Navigate to the credentials page in your [Vapi dashboard](https://dashboard.vapi.ai/keys)
32
+
- Add your Trieve API key for authentication from [Trieve](https://dashboard.trieve.ai/org/keys)
33
+
34
+
2.**Create a New Knowledge Base**
35
+
36
+
- When setting up a new knowledge base, provide:
37
+
- Your Trieve datasetId as the vectorStoreProviderId
38
+
- Appropriate search configuration parameters
39
+
- Vapi will then connect to your existing Trieve vectors
40
+
41
+
Example configuration:
42
+
43
+
```json
44
+
{
45
+
"name": "byok-test",
46
+
"provider": "trieve",
47
+
"vectorStoreSearchPlan": {
48
+
"scoreThreshold": 0.2,
49
+
"searchType": "semantic"
50
+
},
51
+
"vectorStoreProviderId": "<Your datasetId from Trieve>"
52
+
}
53
+
```
54
+
55
+
## Best Practices
56
+
57
+
- Ensure your Trieve API key has appropriate permissions
58
+
- Keep track of which datasetIds correspond to which knowledge bases
59
+
- Monitor vector synchronization to ensure consistency
![fern-api[bot]](https://avatars.githubusercontent.com/in/244756?v=4&size=40){kind=avatar}
0 commit comments