chore: simplify model asset preparation

README.md

@@ -56,10 +56,10 @@ npm install
 ### Prepare Model Assets
 Execute the script per model folder. Make sure Python is installed properly.
 
-First, navigate to the model directory and run the prepare_model.sh script. This script requires an S3 bucket name as an argument, which will be used to upload the model.
+First, navigate to the model directory and run the prepare_model.sh script. This script requires an S3 bucket name as an argument, which will be used to upload the model. Please make sure the bucket name is located in the same region as the CDK deployment.
 
 ```bash
-cd source/model/<rerank/embedding/instruct>/model
+cd source/model/
 ./prepare_model.sh -s <Your S3 Bucket Name>
 ```
 
@@ -87,14 +87,13 @@ Please make sure **docker** is installed and the CDK command is executed in the
 
 ```bash
 cd source/infrastructure
-npx cdk deploy --parameters S3ModelAssets=<Your S3 Bucket Name> --parameters SubEmail=<Your email address> --parameters OpenSearchIndex=<Your OpenSearch Index Name> --parameters EtlImageName=<Your ETL model name> --parameters ETLTag=<Your ETL tag name>
+npx cdk deploy --parameters S3ModelAssets=<Your S3 Bucket Name> --parameters SubEmail=<Your email address> --parameters EtlImageName=<Your ETL model name> --parameters ETLTag=<Your ETL tag name>
 ```
 
 To deploy the offline process only, you can configure context parameters to skip the online process. 
 
 ```bash
-npx cdk deploy --parameters S3ModelAssets=<Your S3 Bucket Name> --parameters SubEmail=<Your email address> --parameters OpenSearchIndex=<Your OpenSearch Index Name> --parameters EtlImageName=<Your ETL model name> --parameters ETLTag=<Your ETL tag name> --context DeploymentMode="OFFLINE_EXTRACT"
-
+npx cdk deploy --parameters S3ModelAssets=<Your S3 Bucket Name> --parameters SubEmail=<Your email address> --parameters EtlImageName=<Your ETL model name> --parameters ETLTag=<Your ETL tag name> --context DeploymentMode="OFFLINE_EXTRACT"
 ```
 
 ## Deployment Parameters
@@ -111,9 +110,8 @@ npx cdk deploy --parameters S3ModelAssets=<Your S3 Bucket Name> --parameters Sub
 
 | Context | Description |
 |---------|-------------|
-| DeploymentMode | The mode for deployment. There are three modes: `OFFLINE_EXTRACT`, `OFFLINE_OPENSEARCH`, and `ALL`. |
-| LayerPipOption | The configuration option for the Python package installer (pip) for the Lambda layer. Please use it when the instance you are using is in China. |
-| JobPipOption | The configuration option for the Python package installer (pip). Please use it when this solution is deployed in GCR region. |
+| DeploymentMode | The mode for deployment. There are three modes: `OFFLINE_EXTRACT`, `OFFLINE_OPENSEARCH`, and `ALL`. Default deployment mode is `ALL`. |
+| LayerPipOption | The configuration option for the Python package installer (pip) for the Lambda layer. Please use it to set PyPi mirror(e.g. -i https://pypi.tuna.tsinghua.edu.cn/simple) when your local development environment is in GCR region. Default LayerPipOption is set to ``. |
 
 
 ## API Reference

source/lambda/executor/utils/context_utils.py

@@ -14,7 +14,7 @@ def contexts_trunc(docs: list[dict], context_num=2):
     docs = [doc for doc in docs[:context_num]]
     # the most related doc will be placed last
     docs.sort(key=lambda x: x["score"])
-    logger.info(f'max context score: {docs[-1]["score"]}')
+    # logger.info(f'max context score: {docs[-1]["score"]}')
     # filter same docs
     s = set()
     context_strs = []

source/lambda/executor/utils/executor_entries/common_entry.py

@@ -113,12 +113,21 @@ def get_qd_chain(qd_config, qd_workspace_list):
     compression_retriever = ContextualCompressionRetriever(
         base_compressor=compressor, base_retriever=lotr
     )
-    qd_chain = chain_logger(
-        RunnablePassthrough.assign(
-            docs=compression_retriever | RunnableLambda(retriever_results_format)
-        ),
-        "qd chain",
-    )
+    if not qd_workspace_list:
+        qd_chain = chain_logger(
+            RunnablePassthrough.assign(
+                docs=RunnableLambda(lambda x: [])
+                | RunnableLambda(retriever_results_format)
+            ),
+            "qd chain",
+        )
+    else:
+        qd_chain = chain_logger(
+            RunnablePassthrough.assign(
+                docs=compression_retriever | RunnableLambda(retriever_results_format)
+            ),
+            "qd chain",
+        )
     return qd_chain