app19

app.py

@@ -72,19 +72,19 @@ vectordb = Chroma.from_documents(
 retriever = vectordb.as_retriever(search_kwargs={"k": 1}, search_type="mmr")
 
 class FinalAnswer(BaseModel):
-    query: str = Field(description="the original query")
+    question: str = Field(description="the original question")
     answer: str = Field(description="the extracted answer")
 
 # Assuming you have a parser for the FinalAnswer class
 parser = PydanticOutputParser(pydantic_object=FinalAnswer)
 
 template = """
-Your name is AngryGreta and you are a recycling chatbot with the objective to anwer querys from user in English or Spanish /
-Use the following pieces of context to answer the query /
-Answer in the same language of the query /
+Your name is AngryGreta and you are a recycling chatbot with the objective to anwer questions from user in English or Spanish /
+Use the following pieces of context to answer the question /
+Answer in the same language of the question /
 Context: {context}
 Chat history: {chat_history}
-User: {query}
+User: {question}
 {format_instructions}
 """
 
@@ -94,7 +94,7 @@ qa_prompt = ChatPromptTemplate(
     messages=[
         sys_prompt,
         MessagesPlaceholder(variable_name="chat_history"),
-        HumanMessagePromptTemplate.from_template("{query}")],
+        HumanMessagePromptTemplate.from_template("{question}")],
     partial_variables={"format_instructions": parser.get_format_instructions()}
 )
 llm = HuggingFaceHub(
@@ -108,7 +108,7 @@ llm = HuggingFaceHub(
     },
 )
 
-memory = ConversationBufferMemory(llm=llm, memory_key="chat_history", input_key='query', output_key='output', return_messages=True)
+memory = ConversationBufferMemory(llm=llm, memory_key="chat_history", input_key='question', output_key='output', return_messages=True)
 
 qa_chain = ConversationalRetrievalChain.from_llm(
     llm = llm,
@@ -122,8 +122,8 @@ qa_chain = ConversationalRetrievalChain.from_llm(
     output_key = 'output',
 )
 
-def chat_interface(query,history):
-    result = qa_chain.invoke({'query': query})
+def chat_interface(question,history):
+    result = qa_chain.invoke({'question': question})
     output_string = result['output']
 
     # Find the index of the last occurrence of "answer": in the string