Introduce FastAPI app for LLM-based research question generation

[leonvanbokhorst]

Summary by Sourcery

New Features:

• Introduce a new FastAPI application for generating research questions using an LLM-based approach with Ollama.

[sourcery-ai]

Reviewer's Guide by Sourcery

This PR introduces a new FastAPI service for generating research questions using the Ollama LLM. The implementation includes a robust error handling system, async client management, and structured request/response models using Pydantic. The service communicates with the Ollama API to generate a main research question and supporting sub-questions based on a given topic.

Sequence diagram for Research Question Generation Process

sequenceDiagram
    actor User
    participant FastAPI
    participant ResearchService
    participant OllamaAPI
    User->>FastAPI: POST /research {topic}
    FastAPI->>ResearchService: generate_research(input_data)
    ResearchService->>OllamaAPI: chat(model, messages)
    OllamaAPI-->>ResearchService: response
    ResearchService->>FastAPI: ResearchResponse
    FastAPI-->>User: ResearchResponse

Loading

Class diagram for Research Question Generation Service

classDiagram
    class ResearchInput {
        +String topic
    }
    class ResearchResponse {
        +String main_question
        +List~String~ sub_questions
    }
    class AsyncClient {
    }
    class FastAPI {
        +String title
        +String description
        +String version
    }
    class HTTPException {
        +int status_code
        +String detail
    }
    class Logger {
        +info(String)
        +error(String)
    }
    class ResearchService {
        +generate_research(ResearchInput) ResearchResponse
        +generate_research_questions(String) Dict
    }
    ResearchService --> ResearchInput
    ResearchService --> ResearchResponse
    ResearchService --> AsyncClient
    ResearchService --> HTTPException
    ResearchService --> Logger
    FastAPI --> ResearchService
    note for ResearchService "Handles research question generation and API endpoint"

Loading

File-Level Changes

Change	Details	Files
Implementation of FastAPI service structure and configuration	Set up FastAPI app with title, description, and version Configure logging system Define Pydantic models for request and response validation	src/08_research_questions.py
Implementation of Ollama client management	Create cached Ollama client instance using lru_cache Implement async context manager for client resource management	src/08_research_questions.py
Implementation of research question generation logic	Create prompt template for research question generation Implement response parsing logic to extract main and sub-questions Add comprehensive error handling and logging Set up API endpoint for research question generation	src/08_research_questions.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time. You can also use
  this command to specify where the summary should be inserted.

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey @leonvanbokhorst - I've reviewed your changes - here's some feedback:

Overall Comments:

• The get_client() context manager has an empty finally block. If no cleanup is needed, consider removing the context manager. If cleanup is needed (e.g., closing the client connection), implement it in the finally block.

Here's what I looked at during the review

• 🟢 General issues: all looks good
• 🟢 Security: all looks good
• 🟢 Testing: all looks good
• 🟢 Complexity: all looks good
• 🟢 Documentation: all looks good

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}