Feature: previous conversational history in future queries

 Great question! Whether to include previous conversational history in future queries depends a lot on your app’s goals and UX. Here’s a quick rundown:

When to include conversation history:

  • Chat-style, interactive assistant: If you want the LLM to maintain context over multiple turns, track follow-ups, or engage in a natural dialogue, including history is essential.

  • Clarification & refinement: History helps the model understand references like “What about the second item?” or “Tell me more about that.”

  • Better user experience: Makes the interaction feel more coherent and human-like.

When not to include history:

  • Strict, isolated Q&A: If each query is independent (e.g., “list all todo items” queries), history can introduce noise or confusion.

  • Privacy / data minimization: You want to limit context to only relevant docs or user input for security or data size reasons.

  • Cost & token limits: Including history increases tokens sent, which raises cost and can hit model limits.

How to do it right:

  • Keep a rolling window of recent exchanges, trimming older ones.

  • Summarize or condense history if it gets long.

  • Optionally, include only key points or user intents rather than full transcripts.

  • Clearly separate the history context from the retrieved documents to avoid mixing unrelated info.

Bottom line:
For your RAG app focused on documents and accuracy, I’d recommend starting without conversational history — just feed the question + relevant retrieved chunks from your own data. This keeps results focused and predictable.

If you later want to add chat-style features or multi-turn dialogs, then implement a manageable history buffer and integrate it carefully.

Want me to help you design a clean way to add optional conversational history later?

Comments

Post a Comment

Popular posts from this blog

Feature: Audit log for one login, and identity service

Image
Customer (Product) Page High-Level System Design Diagram (PlantUML) Sequence Diagram: Audit Event Ingestion Sequence Diagram: Orchestration Event For a High-Level System (Component) Diagram The queue is implemented as message_queue (generic), and the audit log service consumes from it, writing to a dedicated audit_log table. The logging service also consumes from the same message_queue and writes to log_store. Orchestration/other services use the same queue. Summary Table: What Writes Where Event Type Goes Into Consumed By Final Storage audit message_queue Audit Log Service audit_log table log message_queue Logging Service log_store table doc_uploaded message_queue Orchestration Worker (business DB, or triggers next event) ocr_ready message_queue Notification Worker, etc. (notification log, etc.)  Core Tables message_queue – universal event bus (temp buffer) audit_log – immutable audit/compliance events log_store – application logs (op...
Read more

Getting started - Build your data science lab environment

This guide explains how to set up a complete data science environment for the udemy program. A proper setup ensures compatibility and avoids recurring environment issues.  1. Overview Goal : Create a full-featured environment with sufficient resources for all course exercises. Recommendation : Use Anaconda for the most reliable setup. Alternative : Use a Python virtual environment with pip if Anaconda isn’t working. 2. Setup Options Primary (Recommended) Create a dedicated Anaconda environment (isolated, compatible). Alternative Use a standard Python virtualenv + pip (faster but less reliable). 3. Windows Setup Steps Clone Course Repository git clone https://github.com/ed-donner/llm_engineering/ Follow the repository’s README.md instructions for additional setup details. Create Anaconda Environment Inside the llm_engineering folder: conda env create -f environment.yml ⏳ This may take several minutes. Activate the environment: conda activate llms Deactivat...
Read more

QA - Run #1 - Results

Image
# QA Report for Tag QA_July2025_A - **Tag/Commit:** QA_July2025_A (`f32abc1`) - **Date:** 2025-08-01 - **QA Outcomes:** All tests passed except for file upload (see below)... - **Environment:** Windows 10, Python 3.12, requirements.txt as of tag - **Notes:** See log for detailed results. ## Issue Found - **Step:** - **Bug:** - **Log excerpt:** - **Screenshot:** For this QA run, we begin with pristine state by: Stop all services Delete logs.db, and jobs.db Delete all files in doc_store folder Start all services Test, you should see no data on index page, and query should result in no data found error Next, go ahead and upload new1.txt, and after that new2.txt Issue the query: "can you summarize all of the todo items you can find, seperating each one on a single line, with due date first, then title, and description with any details you can augment" Expected Answer: - August 1, 2025: Respond to Amira and discuss weekend plans - August 3, 2025: Go to Somesh class and finish ta...
Read more