Merge pull request #25 from microsoft/20241010_update

Fix formatting for E4T3

docs/04_implement_audio_transcription/0403.md

@@ -78,20 +78,20 @@ The key tasks are as follows:
 
     The completed version of the `generate_embeddings_for_call_contents()` function is as follows:
 
-    ```python
-    def generate_embeddings_for_call_contents(call_contents):
-        """Generate embeddings for call contents. Key assumptions:
-        - Call contents is a single string.
-        - Azure OpenAI endpoint, key, and deployment name stored in Streamlit secrets."""
+   ```python
+   def generate_embeddings_for_call_contents(call_contents):
+       """Generate embeddings for call contents. Key assumptions:
+       - Call contents is a single string.
+       - Azure OpenAI endpoint, key, and deployment name stored in Streamlit secrets."""
 
-        # Normalize the text for tokenization
-        normalized_content = normalize_text(call_contents)
+       # Normalize the text for tokenization
+       normalized_content = normalize_text(call_contents)
 
-        # Call make_azure_openai_embedding_request() with the normalized content
-        response = make_azure_openai_embedding_request(normalized_content)
+       # Call make_azure_openai_embedding_request() with the normalized content
+       response = make_azure_openai_embedding_request(normalized_content)
 
-        return response.data[0].embedding
-    ```
+       return response.data[0].embedding
+   ```
 
     </details>
 
@@ -102,27 +102,27 @@ The key tasks are as follows:
 
     The completed version of the `save_transcript_to_cosmos_db()` function is as follows:
 
-    ```python
-    def save_transcript_to_cosmos_db(transcript_item):
-        """Save embeddings to Cosmos DB vector store. Key assumptions:
-        - transcript_item is a JSON object containing call_id (int), 
-            call_transcript (string), and request_vector (list).
-        - Cosmos DB endpoint, key, and database name stored in Streamlit secrets."""
-
-        cosmos_endpoint = st.secrets["cosmos"]["endpoint"]
-        cosmos_key = st.secrets["cosmos"]["key"]
-        cosmos_database_name = st.secrets["cosmos"]["database_name"]
-        cosmos_container_name = "CallTranscripts"
-
-        # Create a CosmosClient
-        client = CosmosClient(url=cosmos_endpoint, credential=cosmos_key)
-        # Load the Cosmos database and container
-        database = client.get_database_client(cosmos_database_name)
-        container = database.get_container_client(cosmos_container_name)
-
-        # Insert the call transcript
-        container.create_item(body=transcript_item)
-    ```
+   ```python
+   def save_transcript_to_cosmos_db(transcript_item):
+       """Save embeddings to Cosmos DB vector store. Key assumptions:
+       - transcript_item is a JSON object containing call_id (int), 
+           call_transcript (string), and request_vector (list).
+       - Cosmos DB endpoint, key, and database name stored in Streamlit secrets."""
+
+       cosmos_endpoint = st.secrets["cosmos"]["endpoint"]
+       cosmos_key = st.secrets["cosmos"]["key"]
+       cosmos_database_name = st.secrets["cosmos"]["database_name"]
+       cosmos_container_name = "CallTranscripts"
+
+       # Create a CosmosClient
+       client = CosmosClient(url=cosmos_endpoint, credential=cosmos_key)
+       # Load the Cosmos database and container
+       database = client.get_database_client(cosmos_database_name)
+       container = database.get_container_client(cosmos_container_name)
+
+       # Insert the call transcript
+       container.create_item(body=transcript_item)
+   ```
 
     </details>
 
@@ -133,26 +133,26 @@ The key tasks are as follows:
 
     The completed version of the `make_azure_openai_embedding_request()` function is as follows:
 
-    ```python
-    def make_azure_openai_embedding_request(text):
-        """Create and return a new embedding request. Key assumptions:
-        - Azure OpenAI endpoint, key, and deployment name stored in Streamlit secrets."""
-
-        aoai_endpoint = st.secrets["aoai"]["endpoint"]
-        aoai_key = st.secrets["aoai"]["key"]
-        aoai_embedding_deployment_name = st.secrets["aoai"]["embedding_deployment_name"]
-
-        client = openai.AzureOpenAI(
-            api_key=aoai_key,
-            api_version="2024-06-01",
-            azure_endpoint = aoai_endpoint
-        )
-        # Create and return a new embedding request
-        return client.embeddings.create(
-            model=aoai_embedding_deployment_name,
-            input=text
-        )
-    ```
+   ```python
+   def make_azure_openai_embedding_request(text):
+       """Create and return a new embedding request. Key assumptions:
+       - Azure OpenAI endpoint, key, and deployment name stored in Streamlit secrets."""
+
+       aoai_endpoint = st.secrets["aoai"]["endpoint"]
+       aoai_key = st.secrets["aoai"]["key"]
+       aoai_embedding_deployment_name = st.secrets["aoai"]["embedding_deployment_name"]
+
+       client = openai.AzureOpenAI(
+           api_key=aoai_key,
+           api_version="2024-06-01",
+           azure_endpoint = aoai_endpoint
+       )
+       # Create and return a new embedding request
+       return client.embeddings.create(
+           model=aoai_embedding_deployment_name,
+           input=text
+       )
+   ```
 
     </details>
 
@@ -163,46 +163,46 @@ The key tasks are as follows:
 
     The completed version of the `make_cosmos_db_vector_search_request()` function is as follows:
 
-    ```python
-    def make_cosmos_db_vector_search_request(query_embedding, max_results=5, minimum_similarity_score=0.5):
-        """Create and return a new vector search request. Key assumptions:
-        - Query embedding is a list of floats based on a search string.
-        - Cosmos DB endpoint, key, and database name stored in Streamlit secrets."""
-
-        cosmos_endpoint = st.secrets["cosmos"]["endpoint"]
-        cosmos_key = st.secrets["cosmos"]["key"]
-        cosmos_database_name = st.secrets["cosmos"]["database_name"]
-        cosmos_container_name = "CallTranscripts"
-
-        # Create a CosmosClient
-        client = CosmosClient(url=cosmos_endpoint, credential=cosmos_key)
-        # Load the Cosmos database and container
-        database = client.get_database_client(cosmos_database_name)
-        container = database.get_container_client(cosmos_container_name)
-
-        results = container.query_items(
-            query=f"""
-                SELECT TOP {max_results}
-                    c.id,
-                    c.call_id,
-                    c.call_transcript,
-                    c.abstractive_summary,
-                    VectorDistance(c.request_vector, @request_vector) AS SimilarityScore
-                FROM c
-                WHERE
-                    VectorDistance(c.request_vector, @request_vector) > {minimum_similarity_score}
-                ORDER BY
-                    VectorDistance(c.request_vector, @request_vector)
-                """,
-            parameters=[
-                {"name": "@request_vector", "value": query_embedding}
-            ],
-            enable_cross_partition_query=True
-        )
-
-        # Create and return a new vector search request
-        return results
-    ```
+   ```python
+   def make_cosmos_db_vector_search_request(query_embedding, max_results=5,minimum_similarity_score=0.5):
+       """Create and return a new vector search request. Key assumptions:
+       - Query embedding is a list of floats based on a search string.
+       - Cosmos DB endpoint, key, and database name stored in Streamlit secrets."""
+
+       cosmos_endpoint = st.secrets["cosmos"]["endpoint"]
+       cosmos_key = st.secrets["cosmos"]["key"]
+       cosmos_database_name = st.secrets["cosmos"]["database_name"]
+       cosmos_container_name = "CallTranscripts"
+
+       # Create a CosmosClient
+       client = CosmosClient(url=cosmos_endpoint, credential=cosmos_key)
+       # Load the Cosmos database and container
+       database = client.get_database_client(cosmos_database_name)
+       container = database.get_container_client(cosmos_container_name)
+
+       results = container.query_items(
+           query=f"""
+               SELECT TOP {max_results}
+                   c.id,
+                   c.call_id,
+                   c.call_transcript,
+                   c.abstractive_summary,
+                   VectorDistance(c.request_vector, @request_vector) AS SimilarityScore
+               FROM c
+               WHERE
+                   VectorDistance(c.request_vector, @request_vector) > {minimum_similarity_score}
+               ORDER BY
+                   VectorDistance(c.request_vector, @request_vector)
+               """,
+           parameters=[
+               {"name": "@request_vector", "value": query_embedding}
+           ],
+           enable_cross_partition_query=True
+       )
+
+       # Create and return a new vector search request
+       return results
+   ```
 
     </details>