update

first commit

app.py

@@ -0,0 +1,62 @@
+import gradio as gr
+from langchain_community.document_loaders import WebBaseLoader, PyPDFLoader
+from langchain_community.vectorstores import Chroma
+from langchain_community import embeddings 
+from langchain_community.chat_models import ChatOllama
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.output_parsers import PydanticOutputParser
+from langchain.text_splitter import CharacterTextSplitter
+
+def process_input(urls, question):
+    model_local = ChatOllama(model="llama2")
+    # Convert string of URLs to list
+    urls_list = urls.split("\n")
+    docs = [WebBaseLoader(url).load() for url in urls_list]
+    docs_list = [item for sublist in docs for item in sublist]
+    
+    text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=7500, chunk_overlap=100)
+    doc_splits = text_splitter.split_documents(docs_list)
+
+    vectorstore = Chroma.from_documents(
+        documents=doc_splits,
+        collection_name="rag-chroma",
+        embedding=embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text'),
+    )
+    retriever = vectorstore.as_retriever()
+
+    after_rag_template = """Answer the question based only on the following context:
+    {context}
+    Question: {question}
+    """
+    after_rag_prompt = ChatPromptTemplate.from_template(after_rag_template)
+    after_rag_chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | after_rag_prompt
+        | model_local
+        | StrOutputParser()
+    )
+    return after_rag_chain.invoke(question)
+
+import pyttsx3
+engine = pyttsx3.init('sapi5')
+voices = engine.getProperty('voices')
+# print(voices[1].id)
+engine.setProperty('voice', voices[0].id)
+
+
+def speak(audio):
+    engine.say(audio)
+    engine.runAndWait()
+
+
+# Define Gradio interface
+iface = gr.Interface(fn=process_input,
+                     inputs=[gr.Textbox(label="Enter URLs separated by new lines"), gr.Textbox(label="Question")],
+                    #  server_name
+                     outputs="text",
+                     title="Document Query with Ollama",
+                     description="Enter URLs and a question to query the documents.")
+
+iface.launch()