update dependencies

Dockerfile

@@ -4,14 +4,14 @@ FROM python:3.10.10
 WORKDIR /code
 
 # Copy Pipfile
-COPY Pipfile ./
+COPY Pipfile Pipfile.lock ./
 
 # Python PIP Upgrade & Install Dependencies
 RUN pip install --no-cache-dir --upgrade pip \
     && pip install --no-cache-dir pipenv
 
 # Install Python Dependencies
-RUN pipenv install --system --deploy
+RUN pipenv install --system --deploy --ignore-pipfile
 
 # Set up a new user named "user" with user ID 1000
 RUN useradd -m -u 1000 alaye

Pipfile

@@ -4,14 +4,10 @@ verify_ssl = true
 name = "pypi"
 
 [packages]
-gtts = "*"
-speechrecognition = "*"
-pyaudio = "*"
 langchain = "*"
 openai = "*"
 gradio = "*"
 chromadb = "*"
-pydub = "*"
 tiktoken = "*"
 
 [dev-packages]

Pipfile.lock

@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "5c4dc65e2df68cd004dbf6534e64e5bee5bbc76472e4197eef27c46b900a2aae"
+            "sha256": "13faed2031f024c5c36c5227343c2e72f70f9d9577e9d3bd400b2d5ef3a78359"
         },
         "pipfile-spec": 6,
         "requires": {
@@ -715,14 +715,6 @@
             "markers": "platform_machine == 'aarch64' or (platform_machine == 'ppc64le' or (platform_machine == 'x86_64' or (platform_machine == 'amd64' or (platform_machine == 'AMD64' or (platform_machine == 'win32' or platform_machine == 'WIN32')))))",
             "version": "==2.0.2"
         },
-        "gtts": {
-            "hashes": [
-                "sha256:5314f7dedb4230889ff4773edd37e101408497e166982027b8d9582a4585eb4f",
-                "sha256:9132e409603f34d5023458e3e10ce2f5df55498d7a2ee781c9adbe616fbd4152"
-            ],
-            "index": "pypi",
-            "version": "==2.3.2"
-        },
         "h11": {
             "hashes": [
                 "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d",
@@ -1568,23 +1560,6 @@
             ],
             "version": "==3.2.0"
         },
-        "pyaudio": {
-            "hashes": [
-                "sha256:13915faaa780e6bbbb6d745ef0e761674fd461b1b1b3f9c1f57042a534bfc0c3",
-                "sha256:1505d766ee718df6f5a18b73ac42307ba1cb4d2c0397873159254a34f67515d6",
-                "sha256:26bccc81e4243d1c0ff5487e6b481de6329fcd65c79365c267cef38f363a2b56",
-                "sha256:48e29537ea22ae2ae323eebe297bfb2683831cee4f20d96964e131f65ab2161d",
-                "sha256:59cc3cc5211b729c7854e3989058a145872cc58b1a7b46c6d4d88448a343d890",
-                "sha256:87137cfd0ef8608a2a383be3f6996f59505e322dab9d16531f14cf542fa294f1",
-                "sha256:910ef09225cce227adbba92622d4a3e3c8375117f7dd64039f287d9ffc0e02a1",
-                "sha256:c6b302b048c054b7463936d8ba884b73877dc47012f3c94665dba92dd658ae04",
-                "sha256:d294e3f85b2238649b1ff49ce3412459a8a312569975a89d14646536362d7576",
-                "sha256:eb128e4a6ea9b98d9a31f33c44978885af27dbe8ae53d665f8790cbfe045517e",
-                "sha256:ff7f5e44ef51fe61da1e09c6f632f0b5808198edd61b363855cc7dd03bf4a8ac"
-            ],
-            "index": "pypi",
-            "version": "==0.2.13"
-        },
         "pydantic": {
             "hashes": [
                 "sha256:07293ab08e7b4d3c9d7de4949a0ea571f11e4557d19ea24dd3ae0c524c0c334d",
@@ -1632,7 +1607,6 @@
                 "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6",
                 "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f"
             ],
-            "index": "pypi",
             "version": "==0.25.1"
         },
         "pygments": {
@@ -1886,14 +1860,6 @@
             "markers": "python_version >= '3.7'",
             "version": "==1.3.0"
         },
-        "speechrecognition": {
-            "hashes": [
-                "sha256:14131155e8a8ba00ead1b7b9b1a2fa71c845e4db5f9a5f66a33a1bd6c55c6c35",
-                "sha256:7ae9966887d9909ce3e5a0c27ecc3eacfca16fd0c0829f77f552919418e86306"
-            ],
-            "index": "pypi",
-            "version": "==3.10.0"
-        },
         "sqlalchemy": {
             "hashes": [
                 "sha256:0db6734cb5644c55d0262a813b764c6e2cda1e66e939a488b3d6298cdc7344c2",

alaroye/alaroye.py

@@ -5,10 +5,10 @@ import pathlib
 from typing import Any, Dict, List
 
 import gradio as gr
-from gtts import gTTS
-from pydub import AudioSegment
-from pydub.playback import play
-from io import BytesIO
+# from gtts import gTTS
+# from pydub import AudioSegment
+# from pydub.playback import play
+# from io import BytesIO
 from dotenv import find_dotenv, load_dotenv
 from langchain.chains import RetrievalQA
 from langchain.chains.retrieval_qa.base import BaseRetrievalQA
@@ -16,11 +16,10 @@ from langchain.docstore.document import Document
 from langchain.document_loaders import DirectoryLoader, TextLoader
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.llms import OpenAI
-from langchain.memory import ConversationBufferWindowMemory
 from langchain.prompts import PromptTemplate
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import Chroma
-import speech_recognition as sr
+# import speech_recognition as sr
 
 
 # Load environment variables
@@ -45,7 +44,7 @@ class Alaroye:
         self.embeddings = OpenAIEmbeddings()  # type: ignore
         self.llm = OpenAI(temperature=0.1)  # type: ignore
         self.vector_store: Chroma | None = None
-        self.speech_recognizer = sr.Recognizer()
+        # self.speech_recognizer = sr.Recognizer()
         self.retrieval_qa: BaseRetrievalQA | None = None
         self.persist_directory = os.path.join(os.path.dirname(__file__), "Alaroyedb")
         self.prompt_template = """
@@ -164,59 +163,59 @@ Don't try to make up an answer.
         # Return the formatted answer
         return formatted_answer
 
-    def _listen(self) -> str:
-        """
-        Listen to the user.
+    # def _listen(self) -> str:
+    #     """
+    #     Listen to the user.
 
-        Returns
-        -------
-        str
-            The user's input.
-        """
+    #     Returns
+    #     -------
+    #     str
+    #         The user's input.
+    #     """
 
-        # Initialize the microphone
-        mic = sr.Microphone()
+    #     # Initialize the microphone
+    #     mic = sr.Microphone()
 
-        # Listen to the user
-        with mic as source:
-            print("Calibrating microphone...")
-            self.speech_recognizer.adjust_for_ambient_noise(source, duration=5)
+    #     # Listen to the user
+    #     with mic as source:
+    #         print("Calibrating microphone...")
+    #         self.speech_recognizer.adjust_for_ambient_noise(source, duration=5)
 
-            print("Listening...")
-            try:
-                audio = self.speech_recognizer.listen(source, timeout=5)
-                print("Recognizing...")
+    #         print("Listening...")
+    #         try:
+    #             audio = self.speech_recognizer.listen(source, timeout=5)
+    #             print("Recognizing...")
 
-                text = self.speech_recognizer.recognize_google(audio)
+    #             text = self.speech_recognizer.recognize_google(audio)
 
-                return text
-            except Exception as e:
-                bad_response = "Sorry, I didn't catch that. Could you repeat yourself?"
+    #             return text
+    #         except Exception as e:
+    #             bad_response = "Sorry, I didn't catch that. Could you repeat yourself?"
 
-                return bad_response
+    #             return bad_response
 
-    def _speak(self, text: str) -> None:
-        """
-        Speak to the user.
+    # def _speak(self, text: str) -> None:
+    #     """
+    #     Speak to the user.
 
-        Parameters
-        ----------
-        text : str
-            The text to speak to the user.
-        """
+    #     Parameters
+    #     ----------
+    #     text : str
+    #         The text to speak to the user.
+    #     """
 
-        # Generate speech using gTTS
-        tts = gTTS(text=text, lang="de")
+    #     # Generate speech using gTTS
+    #     tts = gTTS(text=text, lang="de")
 
-        # Write the speech to bytes
-        mp3_fp = BytesIO()
-        tts.write_to_fp(mp3_fp)
+    #     # Write the speech to bytes
+    #     mp3_fp = BytesIO()
+    #     tts.write_to_fp(mp3_fp)
 
-        # Play the speech
-        stream = BytesIO(mp3_fp.read())
-        mp3_fp.close()
-        audio = AudioSegment.from_file(stream, format="mp3")
-        play(audio)
+    #     # Play the speech
+    #     stream = BytesIO(mp3_fp.read())
+    #     mp3_fp.close()
+    #     audio = AudioSegment.from_file(stream, format="mp3")
+    #     play(audio)
 
     @staticmethod
     def _get_documents(