Update app.py

app.py

@@ -115,7 +115,7 @@ def rag_chain(llm, prompt, db):
     completion = rag_chain({"query": prompt})
     return completion
 
-def wandb_trace(rag_option, prompt, prompt_template, completion, chain_name):
+def wandb_trace(rag_option, prompt, prompt_template, result, completion, chain_name):
     wandb.init(project = "openai-llm-rag")
     trace = Trace(
         name = chain_name,
@@ -132,7 +132,7 @@ def wandb_trace(rag_option, prompt, prompt_template, completion, chain_name):
         #start_time_ms = start_time_ms,
         #end_time_ms = end_time_ms,
         inputs = {"rag_option": rag_option, "prompt": prompt, "prompt_template": prompt_template},
-        outputs = {"completion": str(completion)},
+        outputs = {"result": str(result), "completion": str(completion)},
     )
     trace.log("test")
     wandb.finish()
@@ -155,7 +155,7 @@ def invoke(openai_api_key, rag_option, prompt):
             completion = rag_chain(llm, prompt, db)
             result = completion["result"]
             prompt_template = rag_template
-            chain_name = type(RetrievalQA).__name__
+            chain_name = type(RetrievalQA)
         elif (rag_option == "MongoDB"):
             #splits = document_loading_splitting()
             #document_storage_mongodb(splits)
@@ -163,17 +163,17 @@ def invoke(openai_api_key, rag_option, prompt):
             completion = rag_chain(llm, prompt, db)
             result = completion["result"]
             prompt_template = rag_template
-            chain_name = type(RetrievalQA).__name__
+            chain_name = type(RetrievalQA)
         else:
             result = llm_chain(llm, prompt)
             completion = result
             prompt_template = llm_template
-            chain_name = type(LLMChain).__name__
+            chain_name = type(LLMChain)
     except Exception as e:
         completion = e
         raise gr.Error(e)
     finally:
-        wandb_trace(rag_option, prompt, prompt_template, completion, chain_name)
+        wandb_trace(rag_option, prompt, prompt_template, result, completion, chain_name)
     return result
 
 description = """<strong>Overview:</strong> Context-aware multimodal reasoning application using a <strong>large language model (LLM)</strong> with