After trying to follow the instructions here with both OpenAI and OpenRouter providers, I finally got it to work by disabling streaming. With OpenRouter, I was able to run a test with the Run test button in the LLM manual config screen for an gpt-4o. But running the test for perplexity/sonar-deep-research resulted in a 502 error and the following output in the console. It took quite a long time for this error to appear (~30 seconds or something) whereas testing other models returns immediately. content_topFrameLifeline.js:1 Loading content_topFrameLifeline.js content_topFrameLifeline.js:1 CONTENT SERVICE LIFELINE: CONNECT content_topFrameLifeline.js:1 CONTENT SERVICE LIFELINE: MESSAGE Object topic.js:404 ℹ️ Discourse v3.5.0.beta3-dev — https://github.com/discourse/discourse/commits/c3795177f2 — Ember v5.12.0 /admin/plugins/discourse-ai/ai-llms:1 Uncaught (in promise) Error: A listener indicated an asynchronous response by returning true, but the message channel closed before a response was received content_topFrameLifeline.js:1 CONTENT SERVICE LIFELINE: TIMEOUT content_topFrameLifeline.js:1 CONTENT SERVICE LIFELINE: CONNECT content_topFrameLifeline.js:1 CONTENT SERVICE LIFELINE: MESSAGE Object test.json:1 Failed to load resource: the server responded with a status of 502 () client-error-handler.js:88 SyntaxError: Unexpected token ' ) at l (client-error-handler.js:88:1) at p (client-error-handler.js:88:1) at v.test (ai-llm-editor-form.js:210:1) l @ client-error-handler.js:88 p @ client-error-handler.js:88 test @ ai-llm-editor-form.js:210 Both of these worked, so I was confused what I was doing wrong: ➜ curl --location 'https://api.perplexity.ai/chat/completions' \ --header 'accept: application/json' \ --header 'content-type: application/json' \ --header 'Authorization: Bearer {token}' \ --data '{ "model": "sonar-deep-research", "messages": [ { "role": "system", "content": "Be precise and concise." }, { "role": "user", "content": "How many stars are there in our galaxy?" } ] }' curl https://openrouter.ai/api/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer {token}" \ -d '{ "model": "perplexity/sonar-deep-research", "messages": [ { "role": "user", "content": "How many stars are in the sky" } ] }' Then I got the following answer from Discourse AI, which helped: It looks like your cURL tests hit OpenRouter’s normal chat endpoint fine—but the Discourse AI “Run test” button actually uses the streaming endpoint by default. If that model (or your OpenRouter plan) doesn’t support streaming, you’ll get a 502 + HTML error blob after a long timeout. To fix it in Admin → Settings → Plugins → Discourse AI / LLM: llm_provider: openrouter llm_provider_url: OpenRouter llm_provider_api_key: YOUR_KEY llm_model: perplexity/sonar-deep-research Turn off streaming so the test (and all calls) use the plain chat endpoint you proved works: • llm_use_streaming = false (This setting lives just below the llm_model dropdown.) With streaming off, “Run test” will POST to /chat/completions (not the /stream variant) and you’ll get back valid JSON immediately instead of a 502 HTML page. If you really need streaming you can point the plugin at OpenRouter’s stream URL— but only if your plan/model supports SSE there: • llm_stream_url: {provider_url}/chat/completions/stream • llm_use_streaming: true Otherwise leave streaming off and you’re all set. The result isn’t great because there is no streaming and the reasoning tokens are output as plain text before the “report” - but it works!

The API is very slow, but it appears to work, see: [Untitled AI bot PM] - AI Conversation - Sam Saffron's Blog AI Conversation with Perplexity/sonar-deep-research: sam: who is sam saffron? creative_bot: Sam Saffron: A Comprehensive Overview of His Career and Contributions to Technology Sam Saffron is a… That said, the bug/issue here is that this is mostly useless till we parse the grounding links and citation urls, this is feasable, but not trivial: [The image displays a structured data representation of a conversational transcript detailing citations and annotations related to Sam Saffron's work. (Captioned by AI)] Worth noting, that one reply linked cost me 70 cents! This is not a cheap model to say the least, I would be super careful with it.

[imagem] sam: Worth noting, that one reply linked cost me 70 cents! This is not a cheap model to say the least, I would be super careful with it. Definitely! I enabled this only for my team on our private, internal instance.

Problemas ao configurar manualmente perplexidade sonar pesquisa profunda

Dev

aas 19 Maio , 2025 08:45 3

Com certeza! Ativei isso apenas para minha equipe em nossa instância privada e interna.

Tópico		Respostas	Vistas
Discourse AI causing new SSL and Connection Reset by Peer errors Bug ai	8	663	5 Abril , 2025
Internal Server Error 500- Manual configuration [ Discourse AI] Product Support ai	7	502	5 Setembro , 2025
Discourse AI: Need to Remove JSON Response to get Antrophic Sonnet 5-working in e.g. semantic search Product Support ai	3	291	9 Julho , 2026
Custom LLMs-Job exception [deepseek-coder-v2:latest does not support tools","type":"api_error","param":null,"code":null] Product Support ai	15	1038	5 Setembro , 2025
Getting discourse ai to work with ollama locally Product Support ai	13	1112	20 Fevereiro , 2025

Problemas ao configurar manualmente perplexidade sonar pesquisa profunda

Related topics