++ .env & easy configuration for multiple variables

new file: LangChain/Retrieval-Augmented-Generation/.env.template modified: LangChain/Retrieval-Augmented-Generation/qa_local_docs.py modified: LangChain/Retrieval-Augmented-Generation/test.py
Daethyra · Oct 12, 2023 · d60d308 · d60d308
1 parent 9034a6b
commit d60d308
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 3 deletions.
diff --git a/LangChain/Retrieval-Augmented-Generation/.env.template b/LangChain/Retrieval-Augmented-Generation/.env.template
@@ -0,0 +1,5 @@
+OPENAI_API_KEY=
+SIMILARITY_THRESHOLD=0.7
+CHUNK_SIZE=500
+CHUNK_OVERLAP=0
+LLM_CHAIN_PROMPT_URL=https://smith.langchain.com/hub/rlm/rag-prompt
diff --git a/LangChain/Retrieval-Augmented-Generation/qa_local_docs.py b/LangChain/Retrieval-Augmented-Generation/qa_local_docs.py
@@ -54,6 +54,7 @@ def _load_env_vars(self):
             self.OPENAI_API_KEY = os.getenv('OPENAI_API_KEY', 'sk-')
             if not self.OPENAI_API_KEY:
                 raise ValueError("OPENAI_API_KEY is missing. Please set the environment variable.")
+            self.LLM_CHAIN_PROMPT_URL = os.getenv('LLM_CHAIN_PROMPT_URL', 'https://smith.langchain.com/hub/rlm/rag-prompt')
         except ValueError as ve:
             print(f"ValueError encountered: {ve}")
             raise
@@ -101,7 +102,7 @@ def load_pdfs_from_directory(self, directory_path: str = 'data/') -> List[List[s
                 retriever=self.vectorstore.as_retriever(),
                 # Pull premade RAG prompt from 
                 # https://smith.langchain.com/hub/rlm/rag-prompt
-                chain_type_kwargs={"prompt": hub.pull("rlm/rag-prompt")}
+                chain_type_kwargs={"prompt": hub.pull(self.LLM_CHAIN_PROMPT_URL)}
             )
             # Return all text splits from PDFs
             return all_splits

diff --git a/LangChain/Retrieval-Augmented-Generation/test.py b/LangChain/Retrieval-Augmented-Generation/test.py
@@ -1,11 +1,17 @@
 import unittest
 from unittest.mock import patch, MagicMock
-from qa_local_docs import PDFProcessor
+from qa_local_docs import PDFProcessor, ChatOpenAI, Chroma, UniversalSentenceEncoder, RetrievalQA
 
 # Assumes that 'data/' directory contains PDFs
 class TestPDFProcessor(unittest.TestCase):
+    # Set up reusable objects
     def setUp(self):
-        self.pdf_processor = PDFProcessor()
+        embeddings = UniversalSentenceEncoder()
+        llm = ChatOpenAI()
+        vectorstore = Chroma()
+        qa_chain = RetrievalQA()
+        # Tie reusable objects together
+        self.pdf_processor = PDFProcessor(embeddings, llm, vectorstore, qa_chain)
 
     def test_load_pdfs_from_directory(self):
         # Test that the method returns a non-empty list