separated files based on function

database_search.py

@@ -0,0 +1,33 @@
+from langchain import OpenAI, SQLDatabase, SQLDatabaseChain
+from langchain.llms import OpenAI
+from api_key import open_ai_key
+from speech_to_text import transcribe
+
+llm = OpenAI(temperature=0, openai_api_key='open_ai_key')
+
+
+#Not sure how the data will be stored, but my idea is that when a question or prompt is asked the audio file will be stored as text which then be fed into the llm 
+#to then query the database and return the answer. 
+
+#estbalish the question to be asked
+question = transcribe
+
+# #I feel like I need another step here so that the model takes the question, goes to the db and knows that it needs to look for the answer to the question
+# # I am wondering if I need to setup an extraction algorithm here, but then how do I link the extraction algorithm to the database?
+# #Creating link to db
+# # I am also wondering if there should be an api for the model to call in order to access the database? Thinking that might be more better?
+def database(transcribe):
+    sqlite_db_path = 'sqlite:///database.db'
+    db = SQLDatabase.from_uri(f'sqlite:///{sqlite_db_path}')
+
+    db_chain = SQLDatabaseChain(llm-llm, database=db)
+
+    db_results = db_chain.run(transcribe)
+    return db_results
+#After retrieving the data from the database, have llm summarize the data and return the answer to the question
+
+if __name__ == '__main__':
+    database(transcribe)
+
+
+

model_response.py

@@ -0,0 +1,28 @@
+from langchain.chains.summarize import load_summarize_chain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from api_key import open_ai_key
+import openai
+from database_search import database
+llm = openai(temperature=0, openai_api_key='open_ai_key')
+
+def model_response(database):
+    with open(database) as file:
+        text = file.read()
+
+
+    text_splitter = RecursiveCharacterTextSplitter(separators = ['\n\n', '\n'], chunk_size = 100, chunk_overlap = 0)
+    docs = text_splitter.create_documents([text])
+
+    chain = load_summarize_chain(llm=llm, chain_type = 'map_reduce')
+
+    output = chain.run(docs)
+
+    #Setup for the model to recevie a question and return the answer
+    context = output
+
+
+    answer = llm(context)
+    #Next part is to take the saved docx file and convert it to an audio file to be played back to the user
+
+if __name__ == '__main__':
+    model_response(database)

speech_to_text.py

@@ -1,12 +1,9 @@
 import openai
 import whisper
-from langchain import OpenAI, SQLDatabase, SQLDatabaseChain
-from langchain.llms import OpenAI
-from langchain.chains.summarize import load_summarize_chain
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+
 from api_key import open_ai_key
 
-llm = OpenAI(temperature=0, openai_api_key='open_ai_key')
+llm = openai(temperature=0, openai_api_key='open_ai_key')
 
 
 
@@ -29,68 +26,5 @@ def transcribe(aud_inp, whisper_lang):
     result = whisper.decode(model, mel, options)
     print(result.text)
     return result 
-#Function to convert speech to text
-
-#These two functions might need to go away but I am not entirely sure yet
-# def transcribe_audio(audio_file_path):
-#     #not sure what the path to the audio file will be so just putting a string as a place holder
-#     with open('audio file path') as audio_file:
-#         transcribtion = openai.Audio.transcribe('whisper-1', audio_file)
-#     return transcribtion['text']
-# #Save the transcribed text to a docx file
-# def save_as_doc(question, filename):
-#     doc=Document()
-#     for key, value in minutes.items():
-#         heading = ' '.join(word.capitalize() for word in key.split('_'))
-#         doc.add_heading(heading, level=1)
-#         doc.add_paragraph(value)
-#         doc.add_page_break()
-#     doc.save(f'{filename}.docx')
-#Not sure how the data will be stored, but my idea is that when a question or prompt is asked the audio file will be stored as text which then be fed into the llm 
-#to then query the database and return the answer. 
-
-#estbalish the question to be asked
-# question = transcribe
-
-# #I feel like I need another step here so that the model takes the question, goes to the db and knows that it needs to look for the answer to the question
-# # I am wondering if I need to setup an extraction algorithm here, but then how do I link the extraction algorithm to the database?
-# #Creating link to db
-# # I am also wondering if there should be an api for the model to call in order to access the database? Thinking that might be more better?
-# sqlite_db_path = 'sqlite:///database.db'
-# db = SQLDatabase.from_uri(f'sqlite:///{sqlite_db_path}')
-
-# db_chain = SQLDatabaseChain(llm-llm, database=db)
-
-# db_results = db_chain.run(transcribe)
-
-#After retrieving the data from the database, have llm summarize the data and return the answer to the question
-
-# with open(db_results) as file:
-#     text = file.read()
-
-
-# text_splitter = RecursiveCharacterTextSplitter(separators = ['\n\n', '\n'], chunk_size = 100, chunk_overlap = 0)
-# docs = text_splitter.create_documents([text])
-
-# chain = load_summarize_chain(llm=llm, chain_type = 'map_reduce')
-
-# output = chain.run(docs)
-
-# #Setup for the model to recevie a question and return the answer
-# context = output
-
-
-# answer = llm(context+question)
-
-
-# def save_as_doc(answer, filename):
-#     doc=Document()
-#     #not sure what the data will look like, as to what the keys and values will be, so just putting a place holder
-#     for key, value in minutes.items():
-#         heading = ' '.join(word.capitalize() for word in key.split('_'))
-#         doc.add_heading(heading, level=1)
-#         doc.add_paragraph(value)
-#         doc.add_page_break()
-#     doc.save(f'{filename}.docx')
-
-#Next part is to take the saved docx file and convert it to an audio file to be played back to the user
+if __name__ == '__main__':
+    transcribe('audio_file_path', 'whisper-1')