LLM API

How to Use the Chat Module This module is built to let you run multiple chat sessions in parallel with an AI model (like gpt-3.5-turbo, deepseek-chat, qwen-plus). Each session belongs to one user, but a user can have multiple sessions at the same time. Think of it like this: You are the user. Each session is like a separate conversation thread. The module will handle running them all at once and can save the results for you. 1. Initialize the Chat chat = Chat(MODEL, try_mode=True) MODEL is the model name you want to use. You can also set options like temperature or add a filter function if you want to change the output style. 2. Add a Prompt chat.use_prompt("Use email format the answer following question? {question}") This sets a system prompt for all sessions. The {question} placeholder will be replaced by each question you send. If the input is a string, but placeholder in the prompt. The placeholder would be ignored and input will be appended in the prompt. 3. Choose the Output Format Save results to file as JSONL: chat.save_to("Translation/translation2.jsonl", disable_return=True).to_json() Writes all answers into a file. ...

September 10, 2025 · 3 min · 460 words · Anton

Entity Matching Theory

Background This blog post discusses the reasoning process I went through while addressing a particular problem in entity matching. Although libraries exist to address this task, my focus here is on the conceptual questions that arise during problem solving. Entity Ambiguity In principle, entity matching should not involve ambiguity. Ambiguity may occur in relations (triplets), but not in the entities themselves. The following discussion focuses on the notion of semantic ambiguity. ...

September 2, 2025 · 5 min · 973 words · Anton

Entity Matching: Solving the Problem of Duplicate Entities in Knowledge Graphs

Entity Matching: Solving the Problem of Duplicate Entities in Knowledge Graphs In this blog, I’ll walk through what entity matching is, why it matters in knowledge graphs, and how I designed an efficient solution—available on my GitHub repo. There are huge issues in the repo (cannot handle large amount of entity), the following ideas are just for reference. Background When working with knowledge graphs (KGs), one of the biggest challenges is that the same entity can appear under different names. ...

September 1, 2025 · 5 min · 892 words · Anton