From 1319944dcd6e4a325289b9474d976dab49df25fb Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Thu, 23 Jan 2025 18:05:45 +0100
Subject: [PATCH] docs: Update .env.template to include llm and embedding
 options

---
 .env.template                                   | 17 ++++++++++++++++-
 .../vector/embeddings/LiteLLMEmbeddingEngine.py |  2 --
 .../databases/vector/embeddings/config.py       |  2 +-
 3 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/.env.template b/.env.template
index 75a57de4d..6ce9fedf9 100644
--- a/.env.template
+++ b/.env.template
@@ -1,12 +1,27 @@
 ENV="local"
 TOKENIZERS_PARALLELISM="false"
-LLM_API_KEY=
+
+# LLM settings
+LLM_API_KEY=""
+LLM_MODEL="openai/gpt-4o-mini"
+LLM_PROVIDER="openai"
+LLM_ENDPOINT=""
+LLM_API_VERSION=""
 
 GRAPHISTRY_USERNAME=
 GRAPHISTRY_PASSWORD=
 
 SENTRY_REPORTING_URL=
 
+# Embedding settings
+EMBEDDING_PROVIDER="openai"
+EMBEDDING_API_KEY=""
+EMBEDDING_MODEL="openai/text-embedding-3-large"
+EMBEDDING_ENDPOINT=""
+EMBEDDING_API_VERSION=""
+EMBEDDING_DIMENSIONS=3072
+EMBEDDING_MAX_TOKENS=8191
+
 # "neo4j" or "networkx"
 GRAPH_DATABASE_PROVIDER="networkx"
 # Not needed if using networkx
diff --git a/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py b/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
index 50dde8e89..cb84337c2 100644
--- a/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
+++ b/cognee/infrastructure/databases/vector/embeddings/LiteLLMEmbeddingEngine.py
@@ -9,8 +9,6 @@ from cognee.infrastructure.databases.exceptions.EmbeddingException import Embedd
 from cognee.infrastructure.llm.tokenizer.Gemini import GeminiTokenizer
 from cognee.infrastructure.llm.tokenizer.HuggingFace import HuggingFaceTokenizer
 from cognee.infrastructure.llm.tokenizer.TikToken import TikTokenTokenizer
-from transformers import AutoTokenizer
-import tiktoken  # Assuming this is how you import TikToken
 
 litellm.set_verbose = False
 logger = logging.getLogger("LiteLLMEmbeddingEngine")
diff --git a/cognee/infrastructure/databases/vector/embeddings/config.py b/cognee/infrastructure/databases/vector/embeddings/config.py
index cb72a46f4..315caf7ef 100644
--- a/cognee/infrastructure/databases/vector/embeddings/config.py
+++ b/cognee/infrastructure/databases/vector/embeddings/config.py
@@ -10,7 +10,7 @@ class EmbeddingConfig(BaseSettings):
     embedding_endpoint: Optional[str] = None
     embedding_api_key: Optional[str] = None
     embedding_api_version: Optional[str] = None
-    embedding_max_tokens: Optional[int] = float("inf")
+    embedding_max_tokens: Optional[int] = 8191
     model_config = SettingsConfigDict(env_file=".env", extra="allow")