linting and formatting cookbooks

projects/Basic-RAG/BasciRAG_CustomPrompt.py

@@ -1,13 +1,14 @@
+"""A cookbook demonstrating how to use a custom prompt with BasicRAG."""
+
 from grag.components.prompt import Prompt
 from grag.rag.basic_rag import BasicRAG
 
 custom_prompt = Prompt(
     input_keys={"context", "question"},
-    template='''Answer the following question based on the given context.
+    template="""Answer the following question based on the given context.
     question: {question}
     context: {context}
     answer: 
-    '''
+    """,
 )
-rag = BasicRAG(doc_chain="stuff",
-               custom_prompt=custom_prompt)
+rag = BasicRAG(doc_chain="stuff", custom_prompt=custom_prompt)

projects/Basic-RAG/BasicRAG_FewShotPrompt.py

@@ -1,29 +1,30 @@
+"""A cookbook demonstrating how to use a custom few-shot prompt with BasicRAG."""
+
 from grag.components.prompt import FewShotPrompt
 from grag.rag.basic_rag import BasicRAG
 
 custom_few_shot_prompt = FewShotPrompt(
     input_keys={"context", "question"},
     output_keys={"answer"},
-    example_template='''
+    example_template="""
     question: {question}
     answer: {answer}
-    ''',
-    prefix='''Answer the following question based on the given context like examples given below:''',
-    suffix='''Answer the following question based on the given context
+    """,
+    prefix="""Answer the following question based on the given context like examples given below:""",
+    suffix="""Answer the following question based on the given context
     question: {question}
     context: {context}
     answer:
-    ''',
+    """,
     examples=[
         {
             "question": "What is the name of largest planet?",
-            "answer": "Jupiter is the largest planet."
+            "answer": "Jupiter is the largest planet.",
         },
         {
             "question": "Who came up with Convolutional Neural Networks?",
-            "answer": "Yann LeCun introduced convolutional neural networks."
-        }
-    ]
+            "answer": "Yann LeCun introduced convolutional neural networks.",
+        },
+    ],
 )
-rag = BasicRAG(doc_chain="stuff",
-               custom_prompt=custom_few_shot_prompt)
+rag = BasicRAG(doc_chain="stuff", custom_prompt=custom_few_shot_prompt)

projects/Basic-RAG/BasicRAG_ingest.py

@@ -1,3 +1,5 @@
+"""A cookbook demonstrating how to ingest pdf files for use with BasicRAG."""
+
 from pathlib import Path
 
 from grag.components.multivec_retriever import Retriever
@@ -8,7 +10,7 @@
 client = DeepLakeClient(collection_name="test")
 retriever = Retriever(vectordb=client)
 
-dir_path = Path(__file__).parent / 'some_dir'
+dir_path = Path(__file__).parent / "some_dir"
 
 retriever.ingest(dir_path)
 # rag = BasicRAG(doc_chain="refine")

projects/Basic-RAG/BasicRAG_refine.py

@@ -1,3 +1,5 @@
+"""A cookbook demonstrating how to use Basic RAG with refine chain."""
+
 from grag.components.multivec_retriever import Retriever
 from grag.components.vectordb.deeplake_client import DeepLakeClient
 from grag.rag.basic_rag import BasicRAG

projects/Basic-RAG/BasicRAG_stuff.py

@@ -1,3 +1,5 @@
+"""A cookbook demonstrating how to use Basic RAG with stuff chain."""
+
 from grag.components.multivec_retriever import Retriever
 from grag.components.vectordb.deeplake_client import DeepLakeClient
 from grag.rag.basic_rag import BasicRAG