Youtube added - further checking required

config/config.py

@@ -58,7 +58,7 @@ class Config(object):
     SUPPORTED_LANGUAGES = ['en', 'fr', 'nl', 'de', 'es']
 
     # supported LLMs
-    SUPPORTED_EMBEDDINGS = ['openai.text-embedding-3-small', 'mistral.mistral-embed']
+    SUPPORTED_EMBEDDINGS = ['openai.text-embedding-3-small', 'openai.text-embedding-3-large', 'mistral.mistral-embed']
     SUPPORTED_LLMS = ['openai.gpt-4o', 'openai.gpt-4-turbo', 'openai.gpt-3.5-turbo', 'mistral.mistral-large-2402']
 
     # Celery settings
@@ -123,6 +123,32 @@ class Config(object):
     Question:
     {question}"""
 
+    GPT3_5_ENCYCLOPEDIA_TEMPLATE = """You have a lot of background knowledge, and as such you are some kind of 
+        'encyclopedia' to explain general terminology. Only answer if you have a clear understanding of the question. 
+        If not, say you do not have sufficient information to answer the question. Use the {language} in your communication.
+        Question:
+        {question}"""
+
+    GPT4_TRANSCRIPT_TEMPLATE = """You are a transcription editor that improves a given transcript on several parts 
+    and returns markdown. Without changing what people say. The transcript is delimited between triple backquotes.
+    Do the following:
+    - divide the transcript into several logical parts. Ensure questions and their answers are in the same logical part.
+    - annotate the text to identify these logical parts using headings (max 2 levels) in the same language as the transcript.
+    - improve errors in the transcript given the context, but leave the text intact.
+    
+    ```{transcript}``` 
+    """
+
+    GPT3_5_TRANSCRIPT_TEMPLATE = """You are a transcription editor that improves a given transcript on several parts 
+        and returns markdown. Without changing what people say. The transcript is delimited between triple backquotes.
+        Do the following:
+        - divide the transcript into several logical parts. Ensure questions and their answers are in the same logical part.
+        - annotate the text to identify these logical parts using headings (max 2 levels) in the same language as the transcript.
+        - improve errors in the transcript given the context, but leave the text intact.
+
+        ```{transcript}``` 
+        """
+
     # SocketIO settings
     # SOCKETIO_ASYNC_MODE = 'threading'
     SOCKETIO_ASYNC_MODE = 'gevent'
@@ -182,6 +208,9 @@ class DevConfig(Config):
     # OpenAI API Keys
     OPENAI_API_KEY = 'sk-proj-8R0jWzwjL7PeoPyMhJTZT3BlbkFJLb6HfRB2Hr9cEVFWEhU7'
 
+    # Groq API Keys
+    GROQ_API_KEY = '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'
+
     # Unstructured settings
     UNSTRUCTURED_API_KEY = 'pDgCrXumYhM3CNvjvwV8msMldXC3uw'
     UNSTRUCTURED_BASE_URL = 'https://flowitbv-16c4us0m.api.unstructuredapp.io'
@@ -209,6 +238,9 @@ class DevConfig(Config):
     # Session settings
     SESSION_REDIS = redis.from_url('redis://redis:6379/2')
 
+    # PATH settings
+    ffmpeg_path = '/usr/bin/ffmpeg'
+
 
 class ProdConfig(Config):
     DEVELOPMENT = False