Ready for dataset evaluation

app/llmops/config.yaml

@@ -11,13 +11,14 @@ etl:
   embedding_model: paraphrase-multilingual-mpnet-base-v2
 rag:
   run_id_chromadb: None
-  chat_model_provider: gemini
+  chat_model_provider: deepseek
 testing:
   query: "如何治疗乳腺癌?"
 evaluation:
-  evaluation_dataset_csv_path: "../../../../data/qa_datasets.csv"
+  evaluation_dataset_csv_path: "../../../../data/qa_dataset_01.csv"
   evaluation_dataset_column_question: question
   evaluation_dataset_column_answer: answer
   ls_chat_model_provider:
   - gemini
+  - deepseek
   - moonshot

app/llmops/src/rag_adaptive_evaluation/run.py

@@ -3,6 +3,8 @@ import logging
 import argparse
 import mlflow
 import shutil
+import langsmith
+
 from decouple import config
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_deepseek import ChatDeepSeek
@@ -10,6 +12,7 @@ from langchain_community.llms.moonshot import Moonshot
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores.chroma import Chroma
 
+
 from typing import List
 from typing_extensions import TypedDict
 
@@ -489,13 +492,16 @@ def go_evaluation(args):
         # Programmatically create a dataset in LangSmith
         client = Client()
 
-        dataset = client.create_dataset(
-            dataset_name = dataset_name,
-            description = "A sample dataset in LangSmith."
-        )
-
-        # Add examples to the dataset
-        client.create_examples(inputs=inputs, outputs=outputs, dataset_id=dataset.id)
+        try:
+            # Create a dataset
+            dataset = client.create_dataset(
+                dataset_name = dataset_name,
+                description = "An evaluation dataset in LangSmith."
+            )
+            # Add examples to the dataset
+            client.create_examples(inputs=inputs, outputs=outputs, dataset_id=dataset.id)
+        except langsmith.utils.LangSmithConflictError:
+            pass
 
         
         args.ls_chat_model_evaluator = None if args.ls_chat_model_evaluator == 'None' else args.ls_chat_model_evaluator.split(',')
@@ -521,7 +527,7 @@ def go_evaluation(args):
         # After running the evaluation, a link will be provided to view the results in langsmith
         experiment_results = client.evaluate(
             target,
-            data = "Sample dataset",
+            data = dataset_name,
             evaluators = ls_evaluators,
             experiment_prefix = "first-eval-in-langsmith",
             max_concurrency = 1,