Add document loaders for various formats and implement loading logic

Author: SayamAlt

Generative AI with Langchain/Document Loaders/Social_Network_Ads.csv

@@ -0,0 +1,8 @@
+from langchain_community.document_loaders import CSVLoader
+
+loader = CSVLoader('Social_Network_Ads.csv')
+
+documents = loader.load()
+
+# print(len(documents))
+print(documents[12].page_content)

Generative AI with Langchain/Document Loaders/books/Building Machine Learning Systems with Python - Second Edition.pdf

@@ -0,0 +1,17 @@
+from langchain_community.document_loaders import DirectoryLoader, PyPDFLoader
+
+loader = DirectoryLoader(
+ path='books',
+ glob="*.pdf",
+ loader_cls=PyPDFLoader
+)
+
+# documents = loader.load()
+documents = loader.lazy_load()
+# print(len(documents))
+
+# print(documents[325].page_content)
+# print(documents[325].metadata)
+
+for doc in documents:
+ print(doc.metadata)

Generative AI with Langchain/Document Loaders/books/SPARK GUIDE.pdf

@@ -0,0 +1,11 @@
+from langchain_community.document_loaders import PyPDFLoader
+
+loader = PyPDFLoader('dl-curriculum.pdf')
+
+documents = loader.load()
+
+# print(documents)
+# print(len(documents))
+
+print(documents[16].metadata)
+print(documents[0].page_content)

Generative AI with Langchain/Document Loaders/books/spark concepts.pdf

@@ -0,0 +1,37 @@
+from langchain_community.document_loaders import TextLoader
+from langchain.chat_models import ChatOpenAI
+from langchain_core.output_parsers import StrOutputParser
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+import os, warnings
+warnings.filterwarnings('ignore')
+
+load_dotenv()
+
+api_key = os.getenv('OPENAI_API_KEY')
+
+model = ChatOpenAI(api_key=api_key)
+
+prompt = PromptTemplate(
+ template='Write a summary for the following poem:\n{poem}',
+ input_variables=['poem']
+)
+
+parser = StrOutputParser()
+
+loader = TextLoader('cricket.txt', encoding='utf-8')
+
+documents = loader.load()
+
+# print(documents)
+# print(type(documents))
+# print(len(documents))
+
+# print(documents[0].metadata)
+# print(documents[0].page_content)
+# print(type(documents[0]))
+
+chain = prompt | model | parser
+
+result = chain.invoke({'poem': documents[0].page_content})
+print(result)