Do Conversational Retrieval QA Chain support custom tool?

[kientv]

It's better to make a external request, example getting order or collect customer data.
One more thing that we can call external API to get info before response to the customer .

[dosubot[bot]]

🤖

Yes, the Conversational Retrieval QA Chain does support the use of custom tools for making external requests such as getting orders or collecting customer data. This is possible through the use of the RemoteLangChainRetriever class, which is designed to retrieve documents from a remote source using a JSON-based API.

Here is an example of how you can initialize the RemoteLangChainRetriever:

// Initialize the remote retriever.
const retriever = new RemoteLangChainRetriever({
  url: "http://0.0.0.0:8080/retrieve", // Replace with your own URL.
  auth: { bearer: "foo" }, // Replace with your own auth.
  inputKey: "message",
  responseKey: "response",
});

In this example, the RemoteLangChainRetriever is used to make external requests to a specified URL with the provided authentication details. The inputKey and responseKey parameters are used to specify the keys for the request and response data respectively.

The RemoteLangChainRetriever also handles errors or failures when making external requests by throwing an error if the response from the request is not okay (i.e., if the HTTP status code is not in the 200-299 range). This is done in the _getRelevantDocuments method.

Therefore, you can use custom tools for making external requests such as getting orders or collecting customer data, as long as you can configure them to work with the RemoteLangChainRetriever or a similar tool.

For more details, you can refer to the source code of the RemoteLangChainRetriever class in the langchainjs repository.

Sources

• examples/src/chains/retrieval_qa_with_remote.ts
• langchain/src/retrievers/remote/remote-retriever.ts
• langchain/src/retrievers/remote/base.ts

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.