From 9348616659526fcd8fff95c5fc55f498b0e01aed Mon Sep 17 00:00:00 2001
From: Zhichang Yu <yuzhichang@gmail.com>
Date: Mon, 25 Nov 2024 14:09:42 +0800
Subject: [PATCH] Handle infinity empty response (#3627)

### What problem does this PR solve?

Handle infinity empty response. Close #3623
Show version in docker build log

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 .github/workflows/tests.yml |  8 ++++++--
 Dockerfile                  |  1 +
 Dockerfile.slim             |  1 +
 rag/utils/infinity_conn.py  | 15 +++++++++++++--
 4 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 2bddf60f7..c7d53763c 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -42,19 +42,23 @@ jobs:
       - name: Ensure workspace ownership
         run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
 
+      # https://github.com/actions/checkout/issues/1781
       - name: Check out code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
 
       - name: Build ragflow:dev-slim
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
           cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data ${RUNNER_WORKSPACE_PREFIX}/libssl*.deb  ${RUNNER_WORKSPACE_PREFIX}/tika-server*.jar* ${RUNNER_WORKSPACE_PREFIX}/chrome* ${RUNNER_WORKSPACE_PREFIX}/cl100k_base.tiktoken .
           sudo docker pull ubuntu:22.04
-          sudo docker build -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
+          sudo docker build --progress=plain -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
 
       - name: Build ragflow:dev
         run: |
-          sudo docker build -f Dockerfile -t infiniflow/ragflow:dev .
+          sudo docker build --progress=plain -f Dockerfile -t infiniflow/ragflow:dev .
 
       - name: Start ragflow:dev-slim
         run: |
diff --git a/Dockerfile b/Dockerfile
index 1e36f0fd9..3595720e0 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -75,6 +75,7 @@ RUN current_commit=$(git rev-parse --short HEAD); \
     else \
         version_info="$version_info full"; \
     fi; \
+    echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
 COPY web web
diff --git a/Dockerfile.slim b/Dockerfile.slim
index d8adffd7f..17da40f61 100644
--- a/Dockerfile.slim
+++ b/Dockerfile.slim
@@ -75,6 +75,7 @@ RUN current_commit=$(git rev-parse --short HEAD); \
     else \
         version_info="$version_info full"; \
     fi; \
+    echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
 COPY web web
diff --git a/rag/utils/infinity_conn.py b/rag/utils/infinity_conn.py
index dddb64975..08fb7c3c3 100644
--- a/rag/utils/infinity_conn.py
+++ b/rag/utils/infinity_conn.py
@@ -48,6 +48,17 @@ def equivalent_condition_to_str(condition: dict) -> str:
     return " AND ".join(cond)
 
 
+def concat_dataframes(df_list: list[pl.DataFrame], selectFields: list[str]) -> pl.DataFrame:
+    """
+    Concatenate multiple dataframes into one.
+    """
+    if df_list:
+        return pl.concat(df_list)
+    schema = dict()
+    for fieldnm in selectFields:
+        schema[fieldnm] = str
+    return pl.DataFrame(schema=schema)
+
 @singleton
 class InfinityConnection(DocStoreConnection):
     def __init__(self):
@@ -289,7 +300,7 @@ class InfinityConnection(DocStoreConnection):
                 kb_res = builder.to_pl()
                 df_list.append(kb_res)
         self.connPool.release_conn(inf_conn)
-        res = pl.concat(df_list)
+        res = concat_dataframes(df_list, selectFields)
         logging.debug("INFINITY search tables: " + str(table_list))
         return res
 
@@ -306,7 +317,7 @@ class InfinityConnection(DocStoreConnection):
             kb_res = table_instance.output(["*"]).filter(f"id = '{chunkId}'").to_pl()
             df_list.append(kb_res)
         self.connPool.release_conn(inf_conn)
-        res = pl.concat(df_list)
+        res = concat_dataframes(df_list, ["id"])
         res_fields = self.getFields(res, res.columns)
         return res_fields.get(chunkId, None)