update

app.py

@@ -8,12 +8,6 @@ es = Elasticsearch(hosts=["https://data.neuralnoise.com:9200"],
                    basic_auth=('elastic', os.environ['ES_PASSWORD']),
                    verify_certs=False, ssl_show_warn=False)
 
-# model_name = "mistralai/Mistral-7B-Instruct-v0.2"
-model_name = "HuggingFaceH4/zephyr-7b-beta"
-
-# Load your language model from HuggingFace Transformers
-generator = pipeline("text-generation", model=model_name)
-
 def search(query, index="pubmed", num_results=3):
     """
     Search the Elasticsearch index for the most relevant documents.
@@ -34,14 +28,17 @@ def search(query, index="pubmed", num_results=3):
     # Extract and return the documents
     docs = [hit["_source"]["content"] for hit in response['hits']['hits']]
 
-    print(f'Received {len(docs)} documents')
+    print(f'Received {len(docs)} documents from index {index}')
 
     return docs
 
-def rag_pipeline(prompt, index="pubmed"):
+def rag_pipeline(prompt, index="pubmed", model_name="HuggingFaceH4/zephyr-7b-beta"):
     """
     A simple RAG pipeline that retrieves documents and uses them to enrich the context for the LLM.
     """
+    # Load your language model from HuggingFace Transformers
+    generator = pipeline("text-generation", model=model_name)
+
     # Retrieve documents
     docs = search(prompt, index=index)
     joined_docs = '\n\n'.join(docs)
@@ -69,7 +66,8 @@ def rag_pipeline(prompt, index="pubmed"):
 iface = gr.Interface(fn=rag_pipeline,
                      inputs=[
                          gr.Textbox(label="Input Prompt", value="Are group 2 innate lymphoid cells (ILC2s) increased in chronic rhinosinusitis with nasal polyps or eosinophilia?"),
-                         gr.Dropdown(label="Elasticsearch Index", choices=["pubmed", "wikipedia", "textbooks"])
+                         gr.Dropdown(label="Index", choices=["pubmed", "wikipedia", "textbooks"], value="pubmed"),
+                         gr.Dropdown(label="Model", choices=["HuggingFaceH4/zephyr-7b-beta", "meta-llama/Llama-2-7b-chat-hf", "meta-llama/Llama-2-13b-chat-hf", "meta-llama/Llama-2-70b-chat-hf"], value="HuggingFaceH4/zephyr-7b-beta")
                      ],
                      outputs=[
                          gr.Textbox(label="Generated Text"),