VHC/HHEM examples with langchain/LlamaIndex #31
Conversation
There was a problem hiding this comment.
Pull Request Overview
This PR adds example notebooks demonstrating how to integrate Vectara's HHEM (Hughes Hallucination Evaluation Model) and VHC (Vectara Hallucination Corrector) with popular RAG frameworks LangChain and LlamaIndex.
- Provides complete integration examples for both LangChain and LlamaIndex workflows
- Demonstrates hallucination detection using HHEM and correction using VHC
- Shows both conservative (no hallucination) and expansive (prone to hallucination) RAG implementations
Reviewed Changes
Copilot reviewed 2 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| notebooks/hallucination_mitigation/vhc-llamaindex-integration.ipynb | Complete LlamaIndex integration example with VectaraClient, dual RAG engines, and pipeline demonstration |
| notebooks/hallucination_mitigation/vhc-langchain-integration.ipynb | Complete LangChain integration example with VectaraClient, dual RAG chains, and pipeline demonstration |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
| "## Summary\n", | ||
| "\n", | ||
| "This notebook demonstrated the integration of Vectara's HHEM and VHC with standard LangChain workflows.\n", | ||
| "We've seen that when a LangChain RAG pipeline hallcuinates, HHEM identifies the hallucination and VHC can correct it.\n", |
There was a problem hiding this comment.
There's a typo in 'hallcuinates' which should be 'hallucinates'.
| "We've seen that when a LangChain RAG pipeline hallcuinates, HHEM identifies the hallucination and VHC can correct it.\n", | |
| "We've seen that when a LangChain RAG pipeline hallucinates, HHEM identifies the hallucination and VHC can correct it.\n", |
Copilot uses AI. Check for mistakes.
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 2 out of 3 changed files in this pull request and generated no new comments.
Comments suppressed due to low confidence (3)
notebooks/hallucination_mitigation/vhc-llamaindex-integration.ipynb:1
- Corrected spelling of 'Devinci' to 'da Vinci'.
{
notebooks/hallucination_mitigation/vhc-langchain-integration.ipynb:1
- Corrected spelling of 'Devinci' to 'da Vinci'.
{
notebooks/hallucination_mitigation/vhc-langchain-integration.ipynb:1
- Corrected spelling of 'Devinci' to 'da Vinci'.
{
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
1 participant
No description provided.