Add the disable report config

Signed-off-by: SimFG <[email protected]>

.github/workflows/unit_test_main.yaml

@@ -93,21 +93,21 @@ jobs:
           export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
           python3 -m pytest -k "not embedding and not processor" --cov=gptcache --cov-report xml:coverage.xml --cov-append ./tests/
 
-      - name: Embedding Unit Tests
+      - name: Processor Unit Tests
         timeout-minutes: 30
         shell: bash
         run: |
           export IS_CI=true
           export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
-          python3 -m pytest --cov=gptcache --cov-report xml:coverage.xml --cov-append ./tests/unit_tests/embedding/
+          python3 -m pytest --cov=gptcache --cov-append --cov-report xml:coverage.xml ./tests/unit_tests/processor/
 
-      - name: Processor Unit Tests
+      - name: Embedding Unit Tests
         timeout-minutes: 30
         shell: bash
         run: |
           export IS_CI=true
           export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
-          python3 -m pytest --cov=gptcache --cov-append --cov-report xml:coverage.xml ./tests/unit_tests/processor/
+          python3 -m pytest --cov=gptcache --cov-report xml:coverage.xml --cov-append ./tests/unit_tests/embedding/
 
       - name: Upload coverage to Codecov
         uses: codecov/[email protected]

examples/data_manager/scalar_store.py

@@ -1,15 +1,15 @@
 import os
+
 import numpy as np
 
-from gptcache.adapter import openai
 from gptcache import cache
+from gptcache.adapter import openai
 from gptcache.manager import get_data_manager, CacheBase, VectorBase
 from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation
 
-
 d = 8
 
-
+# Change the embdding function to your own
 def mock_embeddings(data, **kwargs):
     return np.random.random((d, )).astype('float32')
 

gptcache/adapter/adapter.py

@@ -206,7 +206,7 @@ def post_process():
                 chat_cache.data_manager.add_session(
                     cache_whole_data[2], session.name, pre_embedding_data
                 )
-            if cache_whole_data:
+            if cache_whole_data and not chat_cache.config.disable_report:
                 # user_question / cache_question / cache_question_id / cache_answer / similarity / consume time/ time
                 report_cache_data = cache_whole_data[3]
                 report_search_data = cache_whole_data[2]

gptcache/config.py

@@ -46,6 +46,7 @@ def __init__(
             context_len: Optional[int] = None,
             skip_list: List[str] = None,
             data_check: bool = False,
+            disable_report: bool = False,
     ):
         if similarity_threshold < 0 or similarity_threshold > 1:
             raise CacheError(
@@ -63,3 +64,4 @@ def __init__(
             skip_list = ["system", "assistant"]
         self.skip_list = skip_list
         self.data_check = data_check
+        self.disable_report = disable_report

tests/unit_tests/manager/test_weaviate.py

@@ -26,7 +26,6 @@ def test_normal(self):
         db.mul_add([VectorData(id=size, data=data[0])])
         ret = db.search(data[0])
         self.assertIn(ret[0][1], [0, size])
-        self.assertIn(ret[1][1], [0, size])
         db.delete([0, 1, 2, 3, 4, 5, size])
         ret = db.search(data[0])
         self.assertNotIn(ret[0][1], [0, size])