Dev

[madina1203]

PR Type

enhancement, documentation, configuration changes, tests

---

Description

• Implemented support for different LLMs per agent.

• Added Docker and Streamlit support for deployment.

• Enhanced documentation with setup and usage instructions.

• Introduced automated cleanup for temporary files and database entries.

---

Changes walkthrough 📝

	Relevant files
Enhancement	25 files agents_factory.py Add LLM instance support in agent creation                              +25/-2    agent.py Support specific LLM instance in agent creation                    +3/-2      agent.py Support specific LLM instance in entry agent                          +4/-3      prompt.py Update entry agent prompt for file handling                            +7/-5      prompt.py Update interpreter prompt for spectrum plotting                    +18/-6    tool_spectrum.py Add new tool for spectrum plotting                                              +121/-0  agent.py Support specific LLM instance in SPARQL agent                        +6/-6      prompt.py Update SPARQL prompt for visualization handling                    +1/-1      tool_merge_result.py Update tool merge result for optional parameters                  +1/-1      tool_sparql.py Update SPARQL tool for optional entity parameter                  +1/-1      agent.py Support specific LLM instance in supervisor agent                +2/-2      prompt.py Update supervisor prompt for visualization tasks                  +1/-1      agent.py Support specific LLM instance in validator agent                  +4/-2      prompt.py Update validator prompt for question validity                        +5/-3      RdfGraphCustom.py Add authentication support for SPARQL store                            +3/-2      llm_handler.py Add LLM creation utility for multiple providers                    +47/-0    main.py Refactor main for LLM and endpoint management                        +186/-264 session.py Update session management for MetaboT                                        +13/-13  langraph_workflow.py Refactor workflow for agent and model integration                +151/-107 cleanup_database.py Add script for database cleanup                                                    +18/-0    cleanup_files.py Add script for file cleanup                                                            +44/-0    postgres_database.py Add PostgreSQL database management                                              +95/-0    postgres_tool_database.py Add tool-specific database operations                                        +79/-0    streamlit_app.py Add main Streamlit application                                                      +496/-0  streamlit_utils.py Add utility functions for Streamlit app                                    +337/-0
Miscellaneous	1 files tool_interpreter.py Remove unused code and clean up                                                    +0/-5
Formatting	2 files test_db_connection.py Format code for database connection test                                  +7/-7      tools_database.py Add newline for code clarity                                                          +2/-0
Tests	3 files questions.py Add standard questions for testing                                              +73/-0    evaluation.py Update evaluation script for LangSmith                                      +54/-43  installation_test.py Add installation test script                                                          +12/-0
Configuration changes	8 files .python-version Specify Python version for the project                                      +1/-0      Dockerfile Add Dockerfile for containerization                                            +10/-0    Procfile Add Procfile for Heroku deployment                                              +1/-0      params.ini Update configuration for LLM models                                            +18/-9    params_alternative.ini Add alternative configuration file                                              +55/-0    docker-compose.yml Add Docker Compose configuration                                                  +8/-0      environment.yml Update environment dependencies                                                    +3/-1      setup.sh Add setup script for Streamlit                                                      +12/-0
Documentation	3 files README.md Update README with setup and usage instructions                    +72/-17  mkdocs.yml Update documentation configuration                                              +1/-1      README.md Add README for Streamlit web app                                                  +114/-0
Additional files	1 files __init__.py [link]

---

Need help?

Type /help how to ... in the comments thread for any questions about PR-Agent usage.

Check out the documentation for more information.

[qodo-code-review]

Qodo Merge was enabled for this repository. To continue using it, please link your Git account with your Qodo account here.

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 4 🔵🔵🔵🔵⚪

🔒 No security concerns identified

⚡ Recommended focus areas for review Duplicate Imports The diff shows duplicate import and environment loading calls (e.g. multiple calls to load_dotenv and duplicate imports of create_workflow). Consider consolidating these statements to improve clarity and maintainability. import os import argparse from typing import Any, Dict, Optional from dotenv import load_dotenv from langsmith import Client from pathlib import Path from app.core.workflow.langraph_workflow import create_workflow, process_workflow from app.core.utils import setup_logger import pickle import configparser # Load environment variables load_dotenv() from typing import Any, Optional, Tuple import functools import argparse from langchain_community.chat_models import ChatOpenAI, ChatLiteLLM from dotenv import load_dotenv load_dotenv() import os from langsmith import Client from app.core.graph_management.RdfGraphCustom import RdfGraph from app.core.agents.agents_factory import create_all_agents from app.core.workflow.langraph_workflow import create_workflow, process_workflow from app.core.utils import setup_logger, load_config Docstring Consistency Some newly added key functions (e.g. get_api_key, create_litellm_model, llm_creation, langsmith_setup) include docstrings. Ensure they strictly follow the Google DocString format for arguments, returns, and usage details for documentation tools. def get_api_key(provider: str) -> Optional[str]: """ Get API key for specified provider from environment variables. Args: provider: Provider name matching a key in API_KEY_MAPPING Returns: API key if found, None otherwise """ env_var = API_KEY_MAPPING.get(provider) return os.getenv(env_var) if env_var else None def create_litellm_model(config: configparser.SectionProxy) -> ChatLiteLLM: """ Create a ChatLiteLLM instance based on the model id and configuration. Only uses parameters that are explicitly specified in the configuration. Args: config (configparser.SectionProxy): The configuration section Returns: ChatLiteLLM: Configured ChatLiteLLM instance """ if "id" not in config:

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 5 🔵🔵🔵🔵🔵

🔒 Security concerns No critical security vulnerabilities were identified. However, be cautious to avoid accidental exposure of API keys and other sensitive credentials in logs or client-side messages.

⚡ Recommended focus areas for review Docstring Format Consider ensuring that all key functions and classes (e.g., create_all_agents) include Google-style docstrings. Consistent and clear documentation for parameters, return values, and exceptions will improve code maintainability. def create_all_agents(llms, graph, openai_key=None, session_id=None): """ Dynamically create and initialize all agent modules as specified in the configuration. Parameters: llms (dict): A dictionary mapping LLM keys to their instances. graph: The graph instance used by the agents. openai_key (str, optional): The OpenAI API key to be used by agents. If not provided, it will be read from the environment. session_id (str, optional): A unique session identifier. If not provided, a new user session will be created. Returns: dict: A dictionary mapping agent names to their created executor instances. """ Security Logging Verify that sensitive details such as API keys and credentials are not logged or exposed in error messages. Ensure that logging statements properly mask or exclude confidential information. def llm_creation(api_key: Optional[str] = None) -> Dict[str, ChatOpenAI]: """ Create language models based on configuration parameters. Args: api_key (Optional[str]): The API key for OpenAI. If None, uses environment variable. Returns: Dict[str, ChatOpenAI]: A dictionary containing the language models. """ config = configparser.ConfigParser()

[qodo-code-review]

Qodo Merge was enabled for this repository. To continue using it, please link your Git account with your Qodo account here.

PR Code Suggestions ✨

No code suggestions found for the PR.

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.