Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Add keyless Parallel Search MCP to the Deep Researcher example

Aperta
#966 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 4 giorni

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
35/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
python
Ambito
ai

Direzione di ricerca

Start from the web_research action in the Deep Researcher example, where the Tavily search call and provider choice live, and from the UI's environment check for the Tavily key. The keyless Parallel Search MCP would be a second provider behind that action, with existing Tavily keys and explicit provider choices left unchanged. Done means the research graph runs from search through summarization with each provider, Tavily routing is preserved, and timeout and rate-limit errors surface rather than silently switching providers. Scope and provider design are still open for maintainers, so confirm the approach before writing code.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

status/needs-triage

Is your feature request related to a problem? Please describe.
The Deep Researcher example requires a Tavily API key before its research loop can search the web, including through the UI demo.

Describe the solution you'd like
Add Parallel Search MCP to the existing web_research action. Fresh setups without a Tavily key could use free, keyless search over HTTP, powered by Fast mode. Keep existing Tavily keys and explicit provider choices working. Adapt results to the current source formatting and summarization steps, and update the UI’s environment check. Anonymous access has lower rate limits; surface errors without silently switching providers.

Describe alternatives you've considered
Keep Tavily as the only provider, or connect an MCP client inside a Burr action as discussed in #547. Extending the maintained research loop would give that pattern a concrete user path.

Additional context
Would this scope fit the example? Proposed validation would exercise the research graph through search into summarization, preserve Tavily routing, and check timeout and rate-limit handling.

I work at Parallel.

Lingua principale
Python
Stelle
2.6k
Fork
208
Merge medio
8g 9h
PR unite (30g)
26

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di apache/burr

Tutte le issue di apache/burr

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.