From a9e74dac42708c62f9e0a2d20365934b3bab2107 Mon Sep 17 00:00:00 2001
From: sssaha1989 <150610036+sssaha1989@users.noreply.github.com>
Date: Wed, 6 Aug 2025 10:53:33 -0400
Subject: [PATCH] Update LiteLLMEmbeddingEngine.py (#1205)

This will allow to deal with the issue when the user is using custom
embedding and LLM and passes the hosted_vllm option as part of the
LiteLLM documentation

<!-- .github/pull_request_template.md -->

## Description
<!-- This allows the user to use hosted_vllm with respect to LiteLLM
usage - and only gets applicable for custom embedding models -
specifically Hugging Face models -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---
 .../databases/vector/embeddings/LiteLLMEmbeddingEngine.py       | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py b/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
index cd74525c1..e1109cf1c 100644
--- a/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
+++ b/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
@@ -186,7 +186,7 @@ class LiteLLMEmbeddingEngine(EmbeddingEngine):
             tokenizer = MistralTokenizer(model=model, max_tokens=self.max_tokens)
         else:
             try:
-                tokenizer = HuggingFaceTokenizer(model=self.model, max_tokens=self.max_tokens)
+                tokenizer = HuggingFaceTokenizer(model=self.model.replace('hosted_vllm/',""), max_tokens=self.max_tokens)
             except Exception as e:
                 logger.warning(f"Could not get tokenizer from HuggingFace due to: {e}")
                 logger.info("Switching to TikToken default tokenizer.")