anthropic

app.py

@@ -9,28 +9,53 @@ from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
 from langchain.chains import ConversationalRetrievalChain
 
+
+os.environ['ANTHROPIC_API_KEY'] = os.getenv("Your_Anthropic_API_Key")
 os.environ['OPENAI_API_KEY'] = os.getenv("Your_API_Key")
 
 # Global variable for tracking last interaction time
 last_interaction_time = 0
 
+# Initialize the Anthropic model instead of OpenAI
+from anthropic import LanguageModel
+
+anthropic_model = LanguageModel(api_key=os.environ['ANTHROPIC_API_KEY'], model="some_model")
+
+
+
 def loading_pdf():
     return "Working on the upload. Also, pondering the usefulness of sporks..."
 
 def pdf_changes(pdf_doc):
-    loader = OnlinePDFLoader(pdf_doc.name)
-    documents = loader.load()
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-    texts = text_splitter.split_documents(documents)
-    embeddings = OpenAIEmbeddings()
-    db = Chroma.from_documents(texts, embeddings)
-    retriever = db.as_retriever()
-    global qa 
-    qa = ConversationalRetrievalChain.from_llm(
-        llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo"),  
-        retriever=retriever, 
-        return_source_documents=False)
-    return "Ready"
+    try:
+        if pdf_doc is None:
+            return "No PDF uploaded."
+        
+        loader = OnlinePDFLoader(pdf_doc.name)
+        documents = loader.load()
+        
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+        texts = text_splitter.split_documents(documents)
+        
+        # Replace this with your appropriate embeddings class
+        embeddings = OpenAIEmbeddings()
+        
+        global db
+        db = Chroma.from_documents(texts, embeddings)
+        retriever = db.as_retriever()
+        
+        global qa
+        qa = ConversationalRetrievalChain.from_llm(
+            llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo"),  
+            retriever=retriever, 
+            return_source_documents=False
+        )
+        
+        return "Ready"
+
+    except Exception as e:
+        return f"Error processing PDF: {e}"
+
 
 def clear_data():
     global qa
@@ -44,21 +69,17 @@ def add_text(history, text):
     return history, ""
 
 def bot(history):
-    response = infer(history[-1][0], history)
-    formatted_response = "**Bot:**  \n" + '  \n'.join(response.split('. '))
+    response = infer_anthropic(history[-1][0], history)  # Call the new infer function
+    sentences = '  \n'.join(response.split('. '))
+    formatted_response = f"**Bot:**\n\n{sentences}"
     history[-1][1] = formatted_response
     return history
 
-def infer(question, history):
-    res = []
-    for human, ai in history[:-1]:
-        pair = (human, ai)
-        res.append(pair)
-    
-    chat_history = res
+def infer_anthropic(question, history):
+    chat_history = [(human, ai) for human, ai in history[:-1]]
     query = question
-    result = qa({"question": query, "chat_history": chat_history, "system:":"This is a world-class summarizing AI, be helpful."})
-    return result["answer"]
+    result = anthropic_model.query(query, context=chat_history)
+    return result['answer']
 
 def auto_clear_data():
     global qa, last_interaction_time