Configuring model and data sources
To ensure that your agent delivers accurate results, it is crucial to select the right model and connect relevant data sources. These data sources form the agent's knowledge base.
The platform lets you configure different models and data source types for each agent. You can upload files, connect to cloud storage, or link to website URLs that can be indexed. The agent uses this information to quickly find and return relevant answers to your queries. Your agent can scan through all this information in no time to find solutions to your queries.
Select a language model (LLM)
When creating a new AI agent or editing an existing one, click Model to select a model for your agent. Different models behave differently. Speed, cost, and response quality can vary.
Only the GPT LLMs are provided by Azure OpenAI and they come with enterprise grade privacy features. Here're the details of providers for all supported models:
| Model | Provider | Enterprise Grade Privacy Guarantee |
|---|---|---|
| GPT-5 | Azure OpenAI | Yes |
| GPT-4 | Azure OpenAI | Yes |
| GPT-4 w/Assistant API (Beta) | Azure OpenAI | Yes |
| GPT-3.5 | Azure OpenAI | Yes |
| GPT-3.5 w/ Assistant API (Beta) | Azure OpenAI | Yes |
| GPT 4 Turbo | OpenAI | No |
| Anthropic Claude 2.1 | Anthropic | No |
| Anthropic Claude 3 Opus | Anthropic | No |
| Anthropic Claude 3 Sonnet | Anthropic | No |
| Cohere Command | Cohere | No |
| Cohere Command-R | Cohere | No |
| Cohere Command Light | Cohere | No |
| Llama 2 13B | Replicate | No |
| Llama 2 70B | Replicate | No |
After selecting a model, you can adjust various parameters such as temperature, and the number of input and output tokens.
Keep in mind that LLMs have limitations with complex math and calculations. If your use case involves such tasks, it’s important to test the results carefully to ensure accuracy. If an agent fails or times out repeatedly, it might help to switch the model.
Data sources
After selecting a model, connect different data sources to build a knowledge base for your agent to refer to.
- Previous Data - reuse data sources added for other agents.
- Upload Files - upload files directly from your computer, such as documents, spreadsheets, or PDFs. These files are indexed and used by the agent when responding to queries.
- Website URLs - enter URLs of websites or domains you want to index. The agent can scan and reference content from these pages.
- Google Drive - connect your Google account to import data from your Google Drive .
- Microsoft OneDrive - connect your Microsoft account to import data from your Microsoft OneDrive.
- Confluence and JIRA - connect your Atlassian account to configure Confluence and JIRA to allow the agent to use issues, tickets, and documentation.
- Github - connect GitHub repositories so the agent can reference code, issues, and related documentation.
When using cloud storage or an online data source, you can set a frequency for data refresh. This controls how often data is indexed or pages are refreshed.
Large or complex data sources may affect response time. It is important to test your agent after making changes. Clear and focused data sources produce better results than large, unstructured collections.
After configuring datasources, you can set up additional actions and link tools to your agent.