Fixes and added command line tool to run RAG

level_3/Readme.md

@@ -29,13 +29,15 @@ After that, you can run:
 
 ```docker compose up promethai_mem   ```
 
+``` poetry shell ```
+
 Make sure to run 
 
 ``` python scripts/create_database.py ```
 
 After that, you can run: 
 
-``` python test_runner.py \
+``` python rag_test_manager.py \
     --url "https://www.ibiblio.org/ebooks/London/Call%20of%20Wild.pdf" \
     --test_set "example_data/test_set.json" \
     --user_id "666" \

level_3/example_data/metadata.json

@@ -9,5 +9,5 @@
         "owner": "John Doe",
         "license": "MIT",
         "validity_start": "2023-08-01",
-        "validity_end": "2024-07-31",
+        "validity_end": "2024-07-31"
     }

level_3/rag_test_manager.py

@@ -436,14 +436,32 @@ async def main():
 
     args = parser.parse_args()
 
-    with open(args.test_set, "r") as file:
-        test_set = json.load(file)
+    try:
+        with open(args.test_set, "r") as file:
+            test_set = json.load(file)
+            if not isinstance(test_set, list):  # Expecting a list
+                raise TypeError("Parsed test_set JSON is not a list.")
+    except Exception as e:
+        print(f"Error loading test_set: {str(e)}")
+        return
 
-    with open(args.metadata, "r") as file:
-        metadata = json.load(file)
+    try:
+        with open(args.metadata, "r") as file:
+            metadata = json.load(file)
+            if not isinstance(metadata, dict):
+                raise TypeError("Parsed metadata JSON is not a dictionary.")
+    except Exception as e:
+        print(f"Error loading metadata: {str(e)}")
+        return
 
     if args.params:
-        params = json.loads(args.params)
+        try:
+            params = json.loads(args.params)
+            if not isinstance(params, dict):
+                raise TypeError("Parsed params JSON is not a dictionary.")
+        except json.JSONDecodeError as e:
+            print(f"Error parsing params: {str(e)}")
+            return
     else:
         params = None
 

level_3/vectordb/chunkers/chunkers.py

@@ -1,7 +1,7 @@
 from langchain.document_loaders import PyPDFLoader
 import sys, os
 sys.path.append(os.path.dirname(os.path.abspath(__file__)))
-from level_3.shared.chunk_strategy import ChunkStrategy
+from shared.chunk_strategy import ChunkStrategy
 import re
 def chunk_data(chunk_strategy=None, source_data=None, chunk_size=None, chunk_overlap=None):
 

level_3/vectordb/loaders/loaders.py

@@ -1,8 +1,10 @@
 from io import BytesIO
 import fitz
-# sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
 
-from level_3.vectordb.chunkers.chunkers import chunk_data
+from vectordb.chunkers.chunkers import chunk_data
 from llama_hub.file.base import SimpleDirectoryReader
 
 import requests