ChatOpenAI
Prerequisite
Setup
- Chat Models > drag ChatOpenAI node
 (1) (1) (1) (1) (1) (1) (1)-128a9f302a1e395a2dbe2a7956de6984.png)
- Connect Credential > click Create New
-5340fd8a7ec60f9869f35cc646d80bf5.png)
- Fill in the ChatOpenAI credential
 (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1)-5a5f5549aa0bf58011f14ed2e8594721.png)
- Voila 🎉, you can now use ChatOpenAI node in CiniterFlow
 (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1)-2dddaf1d503671a2da6f83bc63ebfa94.png)
Custom base URL and headers
CiniterFlow supports using custom base URL and headers for Chat OpenAI. Users can easily use integrations like OpenRouter, TogetherAI and others that support OpenAI API compatibility.
TogetherAI
- Refer to official docs from TogetherAI
- Create a new credential with TogetherAI API key
- Click Additional Parameters on ChatOpenAI node.
- Change the Base Path:
 (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (2)-30708c10a8aced2eb966b3f798ea5653.png)
Open Router
- Refer to official docs from OpenRouter
- Create a new credential with OpenRouter API key
- Click Additional Parameters on ChatOpenAI node
- Change the Base Path and Base Options:
 (1) (1) (1) (1) (1) (1) (1) (1) (1) (1) (1)-b432e1c40a2e299dd3ad0f14b3cae552.png)
Custom Model
For models that are not supported on ChatOpenAI node, you can use ChatOpenAI Custom for that. This allow users to fill in model name such as mistralai/Mixtral-8x7B-Instruct-v0.1
-e581536e63ade3a529c86eba109a0521.png)
Image Upload
You can also allow images to be uploaded and analyzed by LLM. Under the hood, CiniterFlow will use OpenAI Vison model to process the image. Only works with LLMChain, Conversation Chain, ReAct Agent, and Conversational Agent.
 (1) (1) (1) (1) (1) (1) (2)-166497b9ac8735b6a05a24b1f4544a22.png)
From the chat interface, you will now see a new image upload button:
-e29c9c197b169f988251bfc67720282e.png)
-7764910b577b79399a49f92478d811d5.png)