stanford-oval / WikiChat
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
Why this job: says: rag; topics: rag
What it does
Large language model (LLM) chatbots like ChatGPT and GPT-4 get things wrong a lot, especially if the information you are looking for is recent ("Tell me about the 2024 Super Bowl.") or about less popular topics ("What are some good movies to watch from [insert your favorite foreign director]?"). WikiChat uses Wikipedia and the following 7-stage pipeline to makes sure its responses are factual. Each numbered stage involves one or more LLM calls.
Get started
pixi shell
python -m spacy download en_core_web_sm
# Spacy is only needed for user simulation- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 1,626
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.1
- Released 18 months ago
- Built with
- Python
- 91% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 78% closed
- 8 still open
- Pull requests
- 17 merged
- 3 waiting
- Releases
- 3
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Andrew-Jang / RAGHub | 2,020 | 3 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 91%
- Jinja 7%
- JavaScript 2%
- CSS <1%
Topics
- natural-language-processing
- chatbot
- nlp
- factuality
- emnlp2023
- rag
- llm
Project record
- JobRAG and search
- StatusListed
- Commits59
- Forks146
- Watching17
- Stars in 28 days+8
- CreatedOct 19, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026