We are currently integrating SQLChat with a locally hosted Ollama model. The request is successfully sent to the Ollama model, and the response is received as confirmed by the debug logs in the handler function. However, when debugging the sendMessageToCurrentConversation function in src/components/ConversationView/index.tsx, the fetch function does not return any response.
This is the response we get from the handler written in src\pages\api\chat.ts:
{"model":"llama3.1","created_at":"2025-02-24T11:32:42.5861613Z","message":{"role":"assistant","content":" CREATE TABLE \"employee\" (\n emp_id SERIAL PRIMARY KEY,\n name TEXT NOT NULL,\n email TEXT UNIQUE NOT NULL,\n job_title TEXT NOT NULL,\n hire_date DATE NOT NULL\n);"},"done_reason":"stop","done":true,"total_duration":18191938800,"load_duration":4233036600,"prompt_eval_count":336,"prompt_eval_duration":6012000000,"eval_count":44,"eval_duration":7394000000}
We debugged the handler function to catch any errors, but it was working fine. But even after receiving the response from ollama, we are still stuck at this:
The response from the Ollama model seems to be correctly formatted and complete. However, it does not propagate back through the fetch function as expected.
We are currently integrating SQLChat with a locally hosted Ollama model. The request is successfully sent to the Ollama model, and the response is received as confirmed by the debug logs in the handler function. However, when debugging the
sendMessageToCurrentConversationfunction insrc/components/ConversationView/index.tsx, the fetch function does not return any response.This is the response we get from the handler written in
src\pages\api\chat.ts:{"model":"llama3.1","created_at":"2025-02-24T11:32:42.5861613Z","message":{"role":"assistant","content":" CREATE TABLE \"employee\" (\n emp_id SERIAL PRIMARY KEY,\n name TEXT NOT NULL,\n email TEXT UNIQUE NOT NULL,\n job_title TEXT NOT NULL,\n hire_date DATE NOT NULL\n);"},"done_reason":"stop","done":true,"total_duration":18191938800,"load_duration":4233036600,"prompt_eval_count":336,"prompt_eval_duration":6012000000,"eval_count":44,"eval_duration":7394000000}We debugged the handler function to catch any errors, but it was working fine. But even after receiving the response from ollama, we are still stuck at this:
The response from the Ollama model seems to be correctly formatted and complete. However, it does not propagate back through the fetch function as expected.