Posts on Saltfish's Blog

Raft Stage2

Sat, 07 Mar 2026 14:19:03 -0500

Last time, we finished the first stage of Raft, sucessfully electing a leader without logs. In stage 2, which is the most difficult stage I think, we need to implement the log replication. Leader will receive the command from the client, append it to its log, and then send AppendEntries RPC to the followers. Followers will append the entries to their logs and reply with success or failure.

The Number of Good Subsets

Fri, 20 Feb 2026 16:22:49 -0500

Link

Problem #

You are given an integer array nums. We call a subset of nums good if its product can be represented as a product of one or more distinct prime numbers.

For example, if nums = [1, 2, 3, 4]:
[2, 3], [1, 2, 3], and [1, 3] are good subsets with products 6 = 2*3, 6 = 2*3, and 3 = 3 respectively.
[1, 4] and [4] are not good subsets with products 4 = 2*2 and 4 = 2*2 respectively.
Return the number of different good subsets in nums modulo 1e9 + 7.

Raft Stage1

Sat, 14 Feb 2026 19:21:01 -0500

Raft #

This time we are following the Raft paper and implementing the first stage of Raft, which is leader election. We will implement the leader election algorithm in a simple way, without any optimizations. We will explain all detailed explanation about raft paper in another posts. Our basic code structure is provided by 6.824. So we will not provide the code here, but we will explain the main idea of the leader election algorithm.

Merge Two Binary Tree

Sat, 14 Feb 2026 19:04:39 -0500

Link Merge Two Binary Trees

Problem #

You are given two binary trees root1 and root2.

Imagine that when you put one of them to cover the other, some nodes of the two trees are overlapped while the others are not. You need to merge the two trees into a new binary tree. The merge rule is that if two nodes overlap, then sum node values up as the new value of the merged node. Otherwise, the NOT null node will be used as the node of the new tree.

Stone Game

Fri, 13 Feb 2026 19:46:40 -0500

Link: Stone Game

Problem #

Alice and Bob play a game with piles of stones. There are an even number of piles arranged in a row, and each pile has a positive integer number of stones piles[i].

The objective of the game is to end with the most stones. The total number of stones across all the piles is odd, so there are no ties.

Usage of Entry Level GPU

Thu, 12 Feb 2026 18:16:43 -0500

Our chat system collapsed under 20 concurrent requests

Currently, I’m working on a RAG(Retrieval Augmented Generation) project, while most of the process is done by calling api, the only computation intensive part is the reranking process, which is a method to rank the retrieved documents based on their relevance to the query. In this step we called BAAI/bge-reranker-v2-m3 model locally.

Split a String in Balanced Strings

Thu, 12 Feb 2026 18:06:47 -0500

Problem Link: Split a String in Balanced Strings

Problem #

Balanced strings are those that have an equal quantity of ‘L’ and ‘R’ characters.

Given a balanced string s, split it into some number of substrings such that:

Each substring is balanced. Return the maximum number of balanced strings you can obtain.

Stone Game II

Wed, 11 Feb 2026 16:57:25 -0500

Stone Game II #

Link: Stone Game II

Problem #

Alice and Bob continue their games with piles of stones. There are a number of piles arranged in a row, and each pile has a positive integer number of stones piles[i]. The objective of the game is to end with the most stones.

How to use Microsoft AI Foundry with Langchain

Tue, 10 Feb 2026 14:53:56 -0500

In Microsoft’s AI Foundry, it might be a bit tricky to get it work with Langchain at first. What need to be specified is different model provider has different service endpoint and need to use different class to call the API.

Azure OpenAI #

from langchain_openai import AzureChatOpenAI

llm = AzureChatOpenAI(
 azure_deployment="gpt-5.2-chat", 
 azure_endpoint="https://<your-service>.cognitiveservices.azure.com/",
 api_version="2024-05-01-preview",
 api_key="<your-api-key>", 
 max_tokens=4096,
)

api_key use AZURE_OPENAI_KEY environment variable or pass it directly
azure_endpoint use AZURE_OPENAI_ENDPOINT environment variable or pass it directly

Anthropic #

from langchain_anthropic import AnthropicChat
llm = AnthropicChat(
 base_url="https://<your-service>.services.ai.azure.com/anthropic/", 
 api_key="<your-api-key>",
 model="claude-sonnet-4-5",
)

api_key use ANTHROPIC_API_KEY environment variable or pass it directly
base_url use ANTHROPIC_API_URL then ANTHROPIC_BASE_URL environment variable or pass it

AIChat #

from langchain_azure_ai import AzureAIChatCompletionModel
llm = AzureAIChatCompletionModel(
 azure_endpoint="https://<your-service>.services.ai.azure.com/models",
 azure_deployment="gpt-5.2-chat", 
 api_version="2024-05-01-preview"
)

Need to set AZURE_AI_ENDPOINT to https://<your-service>.services.ai.azure.com/models
API key use AZURE_AI_CREDENTIAL environment variable

Actually, this method is not recommended, because it does not support some features and have poor compatibility to the langchain ecosystem.

My First Post

Mon, 09 Feb 2026 22:47:43 -0500

Start using hugo to write down some tehc blogs!

I will try my best to keep it 100% human written!