DefangLabs / DefangLabs/docs-chatbot
Chatbot not answering vague questions well
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1
- Forks
- 1
- Avg merge
- 14h 50m
- Merged PRs (30d)
- 21
Description
The chatbot currently seems to not answer vague questions as well, e.g. "Does Defang have an MCP sample?". This is likely due to how the algorithm (cosine similarity) decides which information sources (i.e. docs/blog pages) are relevant to the query to formulate an answer.
A potential solution would be to use a different search algorithm, such as hybrid search with LlamaIndex that combines both semantic search (cosine similarity) and keyword search to determine similarity.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named. Start by locating the current cosine-similarity source-selection path, then review the linked LlamaIndex hybrid-search approach; done means vague questions such as the MCP-sample example use relevant sources and produce a better answer.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, search
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100