Added RunAgent Cloud support#79
Merged
Merged
Conversation
- Updated all SDK versions to 0.1.24 - Generated changelog with git-cliff
|
Caution Review failedThe pull request is closed. WalkthroughThis PR introduces six comprehensive example applications to the RunAgent framework: a multi-agent stock trading simulator, AI-driven lead generation workflows, an automated book writing system, a lead scoring SaaS platform, a vector-based retrieval system with streaming, and a multimodal knowledge management agent. Each example includes end-to-end implementations with backend services, frontends, databases, and SDK examples in Python and/or Rust. Changes
Sequence Diagram(s)sequenceDiagram
participant Agent as Trading Agent
participant Secretary as Secretary Validator
participant LLM as LLM (GPT/Gemini)
participant Stock as Stock Model
participant Record as Excel Logger
Agent->>Secretary: plan_loan(date, prices, forum)
Secretary->>LLM: build_loan_prompt()
LLM-->>Secretary: loan_decision_json
Secretary->>Secretary: check_loan(response, max_amount)
alt Valid
Secretary-->>Agent: (true, "", loan_json)
Agent->>Agent: apply_loan(cash, loan_list)
Agent->>Record: create_trade_record()
else Invalid
Secretary-->>Agent: (false, error_msg, {})
Agent->>Agent: retry_or_fail()
end
Agent->>Stock: plan_stock(date, time, prices)
Stock->>LLM: build_action_prompt()
LLM-->>Stock: buy/sell/no_action
Stock->>Secretary: check_action(response, cash, holdings)
alt Valid Action
Secretary-->>Stock: (true, "", action_json)
Stock->>Agent: execute_buy/sell
Agent->>Record: log_transaction()
else Invalid
Secretary-->>Stock: (false, error_msg, {})
Stock->>Agent: retry()
end
sequenceDiagram
participant User as User
participant Frontend as Lead Scoring UI
participant Backend as Flask/Axum Backend
participant RunAgent as RunAgent Client
participant Crew as LeadScoreCrew
User->>Frontend: Upload CSV + Configure
Frontend->>Frontend: Parse & Map Columns
User->>Frontend: Submit (top_n, generate_emails)
Frontend->>Backend: POST /api/score-leads (candidates, params)
Backend->>RunAgent: initialize_client(entrypoint: lead_score_flow)
RunAgent->>Crew: run_flow(candidates, top_n, job_description)
Crew->>Crew: score_all_candidates_async()
Crew-->>RunAgent: {top_candidates, all_candidates, emails}
RunAgent-->>Backend: result
Backend-->>Frontend: scores_json
Frontend->>Frontend: Render Top Candidates Table
Frontend->>User: Offer Download (CSV, Emails)
sequenceDiagram
participant User as User
participant Backend as Flask Backend
participant Agent as RAGRouterAgent
participant VectorDB as Qdrant (3 Collections)
participant LLM as LLM Chain
participant Fallback as Web Search/LLM
User->>Backend: POST /api/query (question)
Backend->>Agent: query(question)
Agent->>Agent: route_query(question)
alt High Confidence Vector Match
Agent->>VectorDB: search(question, k=3) → [products|support|finance]
else Use Router Agent
Agent->>LLM: route_via_agent(question)
LLM-->>Agent: determined_db
end
Agent->>VectorDB: retrieve_documents(db_collection)
Agent->>LLM: rag_chain(question, documents)
LLM-->>Agent: answer
alt Success
Agent-->>Backend: {success: true, answer, source, docs}
else No Good Match
Agent->>Fallback: web_search(question)
Fallback-->>Agent: web_results
Agent->>LLM: summarize_web(results)
LLM-->>Agent: answer
Agent-->>Backend: {success: true, answer, source: "web"}
end
Backend-->>User: json_response
Estimated code review effort🎯 5 (Critical) | ⏱️ ~120 minutes This PR introduces substantial, heterogeneous complexity across six distinct example systems with high logic density:
Areas requiring extra attention:
Possibly related PRs
Poem
✨ Finishing touches
🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro ⛔ Files ignored due to path filters (17)
📒 Files selected for processing (107)
⛔ Files not processed due to max files limit (19)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit