diff --git a/.env.template b/.env.template
index f91a75c7613e4262fb3cf6d2f8154041d043a924..b42cfed6550dc82aed13f93fd582dba902520b44 100644
--- a/.env.template
+++ b/.env.template
@@ -4,6 +4,10 @@ PHOENIX_PORT=6006
 # API KEY TO OPENAI / CHATGPT API
 OPENAI_API_KEY=sk-hj8dfs8f9dsfsdgibberish
 
+# PATH TO LOCALLY INSTALLED OLLAMA DAEMON
+# to use a LLM via OLLAMA it must be installed already
+OLLAMA_API_BASE=http://localhost:11434
+
 #CHUNK SIZE OF DOMAIN FILES
 DOCUMENTS_CHUNK_SIZE=512
 
diff --git a/evaluateRAG.py b/evaluateRAG.py
index a096e584e4367bcb4978b71783124ad9ad8334d0..45886c9b67691102f3168beaad578f6bae5a2b23 100644
--- a/evaluateRAG.py
+++ b/evaluateRAG.py
@@ -21,7 +21,7 @@ nest_asyncio.apply()
 from colorist import Color, BrightColor, bright_yellow, magenta, red, green
 # phoenix is the framework & webservice from arize (https://docs.arize.com/phoenix)
 import phoenix as px
-from phoenix.evals import OpenAIModel, llm_generate, HallucinationEvaluator, QAEvaluator, run_evals
+from phoenix.evals import OpenAIModel, LiteLLMModel, llm_generate, HallucinationEvaluator, QAEvaluator, run_evals
 from phoenix.session.evaluation import get_retrieved_documents, get_qa_with_reference
 from phoenix.evals import RelevanceEvaluator, run_evals
 from phoenix.trace import DocumentEvaluations, SpanEvaluations
@@ -114,7 +114,7 @@ nodes = node_parser.get_nodes_from_documents(documents)
 vector_index = VectorStoreIndex(nodes)
 print(f'created {length_hint(nodes)} chunks')
 countQuestions = length_hint(nodes) * int(os.environ['QUESTIONS_PER_CHUNK'])
-# # Build a QueryEngine and start querying.
+# Build a QueryEngine and start querying.
 query_engine = vector_index.as_query_engine()
 
 ##########
@@ -153,11 +153,12 @@ def output_parser(response: str, index: int):
     return {"__error__": str(e)}
   
 # prompt template to LLM and store > questions_df 
+# You can choose among multiple models supported by LiteLLM (https://docs.litellm.ai/docs/providers)
 questions_df = llm_generate(
   dataframe=document_chunks_df,
   template=generate_questions_template,
-  model=OpenAIModel(
-    model="gpt-3.5-turbo",
+  model=LiteLLMModel(
+    model="ollama/llama2",
   ),
   output_parser=output_parser,
   concurrency=20,
diff --git a/using_llamaindex_with_huggingface_models.ipynb b/using_llamaindex_with_huggingface_models.ipynb
new file mode 100755
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391