0.9.2 | Search Improvements

Changelogs:

* chore: made consistent versioning

* fix: do not send data when both title and value is None

* feat: donot show result if score=0

* fix: fixed unittests

README.md

@@ -89,13 +89,18 @@ This project is licensed under the terms of the Apache License. See the LICENSE
 
 ## Development and Maintanence
 
-### Bump 0.9.1
+### 0.9.2
+
+- [X] restrict send to db if EMPTY title and content
+- [X] Do not show result when score is 0
+
+### 0.9.1
 
 - [X] Error handling
 - [X] Consistency in logs
 - [X] Local db enable
 
-### Bump 0.10+
+### 0.10+
 
 - [ ] Distributed query processing
 - [ ] Caching locally
@@ -104,35 +109,35 @@ This project is licensed under the terms of the Apache License. See the LICENSE
 - [ ] Use unified crawler system in master-slave arch
 - [ ] Create Storage abstraction classes for local and remote client
 
-### Bump 9
+### 0.9
 
 - [X] TF-idf only on title
 - [X] Better similarity measure on content
 - [X] Generalize Storage Class
 
-### Bump 8
+### 0.8
 
 - [X] Optimize the deployment
 - [X] Remove the nltk processing
 - [X] Refactor the codebase
 - [X] Migrate from local_db to cloud Phase-1
 - [X] Optimize the user interface
 
-### Bump 7
+### 0.7
 
 - [X] Replace content with meta data (perhaps?)
 - [X] Extract background worker sites from env
 - [X] AI support Beta
 - [X] Template optimizations
 
-### Bump 6
+### 0.6
 
 - [ ] Extract timestamp and sort accordingly
 - [X] Remote crawler service (use background workers)
 - [X] Analyze the extractable metadata
 - [X] Error Logger to supabase for analytics
 
-### Bump 5-
+### 0.5-
 
 - [X] Don't download everytime query engine is started
 - [ ] Crawler doesn't follow the schema of remote_db

phantom/core/query_engine.py

@@ -34,6 +34,7 @@ def __init__(self, filename="indexed", title_path=None):
 
         self.CONTENT_WEIGHT = int(os.environ.get("CONTENT_WEIGHT", 1))
         self.TITLE_WEIGHT = int(os.environ.get("TITLE_WEIGHT", 2))
+        self.TIME_WEIGHT = int(os.environ.get("TIME_WEIGHT", 5))
 
         self.data = {}
         self.load(filename)
@@ -84,6 +85,12 @@ def query(self, query, count=10):
         # Return the top n results
         final_results = []
         for doc, score in ranked_docs[:count]:
+
+            # send only if score > 0
+                # Hence may get results < count
+            if score == 0:
+                continue
+
             try:
                 title = self.titles[doc] if self.title_table else doc
                 final_results.append((doc, score, title))

phantom/utils/storage.py

@@ -31,7 +31,10 @@ def __init__(self, table_name="index", resume=False, remote_db=True):
         print("DB Ready")
 
     def add(self, key, value, title=None):
-        # TODO: Genaralize the function to accept any table name
+        # TODO: Generalize the function to accept any table name
+        if not value and not title:
+            return False
+
         if self.remote_db:
             try:
                 data, count = (

tests/test_utils.py

@@ -11,8 +11,8 @@
 class TestLogger(unittest.TestCase):
     def test_log(self):
         logger = Logger(show_logs=True, author="John")
-        logger.log("Test log", param1="value1", param2="value2")
-        expected_log = f"{time.strftime('%H:%M:%S')} : John : Test log | {{'param1': 'value1', 'param2': 'value2'}}"
+        logger.log("Test log", param1="value1", param2="value2", origin="test")
+        expected_log = f"{time.strftime('%H:%M:%S')} : John-test : Test log | {{'param1': 'value1', 'param2': 'value2'}}"
         self.assertIn(expected_log, logger.logs)
 
     def test_save(self):
@@ -23,8 +23,8 @@ def test_save(self):
         with open("test_logs.txt", "r") as f:
             saved_logs = f.readlines()
         expected_logs = [
-            f"{time.strftime('%H:%M:%S')} : Jane : Test log 1 | {{'param1': 'value1'}}\n",
-            f"{time.strftime('%H:%M:%S')} : Jane : Test log 2 | {{'param2': 'value2'}}\n",
+            f"{time.strftime('%H:%M:%S')} : Jane- : Test log 1 | {{'param1': 'value1'}}\n",
+            f"{time.strftime('%H:%M:%S')} : Jane- : Test log 2 | {{'param2': 'value2'}}\n",
         ]
         self.assertEqual(saved_logs, expected_logs)