reformat python code samples (#380)

Co-authored-by: Max Shkutnyk <max@lightsonsoftware.com> Co-authored-by: trentfowlercohere <141260477+trentfowlercohere@users.noreply.github.com>
cohere-ai · Jan 23, 2025 · 847b2ef · 847b2ef
1 parent 60d68b8
commit 847b2ef
Show file tree

Hide file tree

Showing 12 changed files with 201 additions and 142 deletions.
diff --git a/fern/pages/-ARCHIVE-/old-tutorials/semantic-search.mdx b/fern/pages/-ARCHIVE-/old-tutorials/semantic-search.mdx
@@ -37,9 +37,9 @@ You can find the code in the <a target="_blank" href="https://github.com/cohere-
 ### 1. Download the Dependencies
 
 ```python PYTHON
-# Install Cohere for embeddings, Umap to reduce embeddings to 2 dimensions, 
+# Install Cohere for embeddings, Umap to reduce embeddings to 2 dimensions,
 # Altair for visualization, Annoy for approximate nearest neighbor search
-pip install cohere umap-learn altair annoy datasets tqdm
+!pip install cohere umap-learn altair annoy datasets tqdm
 ```
 
 And if you're running an older version of the SDK, you might need to upgrade it like so:
@@ -63,7 +63,7 @@ Get your Cohere API key by [signing up here](https://os.cohere.ai/register). Pas
 #### 1a. Import the Necessary Dependencies to Run this Example
 
 ```python PYTHON
-#title Import libraries (Run this cell to execute required code) {display-mode: "form"}
+# title Import libraries (Run this cell to execute required code) {display-mode: "form"}
 
 import cohere
 import numpy as np
@@ -76,8 +76,9 @@ import altair as alt
 from sklearn.metrics.pairwise import cosine_similarity
 from annoy import AnnoyIndex
 import warnings
-warnings.filterwarnings('ignore')
-pd.set_option('display.max_colwidth', None)
+
+warnings.filterwarnings("ignore")
+pd.set_option("display.max_colwidth", None)
 ```
 
 ### 2. Get the Archive of Questions
@@ -128,9 +129,11 @@ input_type_embed = "search_document"
 co = cohere.Client(api_key)
 
 # Get the embeddings
-embeds = co.embed(texts=list(df['text']),
-                  model=model_name,
-                  input_type=input_type_embed).embeddings
+embeds = co.embed(
+    texts=list(df["text"]),
+    model=model_name,
+    input_type=input_type_embed,
+).embeddings
 ```
 
 ### 4. Build the Index, search Using an Index and Conduct Nearest Neighbour Search
@@ -141,13 +144,13 @@ Let's build an index using the library called annoy. Annoy is a library created
 
 ```python PYTHON
 # Create the search index, pass the size of embedding
-search_index = AnnoyIndex(np.array(embeds).shape[1], 'angular')
+search_index = AnnoyIndex(np.array(embeds).shape[1], "angular")
 
 # Add all the vectors to the search index
 for i in range(len(embeds)):
     search_index.add_item(i, embeds[i])
-search_index.build(10) # 10 trees
-search_index.save('test.ann')
+search_index.build(10)  # 10 trees
+search_index.save("test.ann")
 ```
 
 After building the index, we can use it to retrieve the nearest neighbours either of existing questions (section 3.1), or of new questions that we embed (section 3.2).
@@ -161,15 +164,21 @@ If we're only interested in measuring the similarities between the questions in
 example_id = 92
 
 # Retrieve nearest neighbors
-similar_item_ids = search_index.get_nns_by_item(example_id,10,
-                                                include_distances=True)
+similar_item_ids = search_index.get_nns_by_item(
+    example_id, 10, include_distances=True
+)
 
 # Format and print the text and distances
-results = pd.DataFrame(data={'texts': df.iloc[similar_item_ids[0]]['text'],
-                             'distance': similar_item_ids[1]}).drop(example_id)
-
+results = pd.DataFrame(
+    data={
+        "texts": df.iloc[similar_item_ids[0]]["text"],
+        "distance": similar_item_ids[1],
+    }
+).drop(example_id)
+
+# NOTE: Your results might look slightly different to ours.
 print(f"Question:'{df.iloc[example_id]['text']}'\nNearest neighbors:")
-print(results) # NOTE: Your results might look slightly different to ours.
+print(results)
 ```
 
 ```
@@ -199,20 +208,26 @@ query = "What is the tallest mountain in the world?"
 input_type_query = "search_query"
 
 # Get the query's embedding
-query_embed = co.embed(texts=[query],
-                  model=model_name,
-                  input_type=input_type_query).embeddings
+query_embed = co.embed(
+    texts=[query], model=model_name, input_type=input_type_query
+).embeddings
 
 # Retrieve the nearest neighbors
-similar_item_ids = search_index.get_nns_by_vector(query_embed[0],10,
-                                                include_distances=True)
+similar_item_ids = search_index.get_nns_by_vector(
+    query_embed[0], 10, include_distances=True
+)
 # Format the results
-query_results = pd.DataFrame(data={'texts': df.iloc[similar_item_ids[0]]['text'], 
-                             'distance': similar_item_ids[1]})
+query_results = pd.DataFrame(
+    data={
+        "texts": df.iloc[similar_item_ids[0]]["text"],
+        "distance": similar_item_ids[1],
+    }
+)
 
 
+# NOTE: Your results might look slightly different to ours.
 print(f"Query:'{query}'\nNearest neighbors:")
-print(query_results) # NOTE: Your results might look slightly different to ours.
+print(query_results)
 ```
 
 |     | texts                                                                        | distance |
@@ -233,32 +248,28 @@ print(query_results) # NOTE: Your results might look slightly different to ours.
 Use the code below to create a visualization of the embedded archive. As written, this code will only run in a jupyter notebook.
 
 ```python PYTHON
-#@title Plot the archive {display-mode: "form"}
+# @title Plot the archive {display-mode: "form"}
 
 # UMAP reduces the dimensions from 1024 to 2 dimensions that we can plot
-reducer = umap.UMAP(n_neighbors=20) 
+reducer = umap.UMAP(n_neighbors=20)
 umap_embeds = reducer.fit_transform(embeds)
 
 # Prepare the data to plot and interactive visualization
 # using Altair
-df_explore = pd.DataFrame(data={'text': df['text']})
-df_explore['x'] = umap_embeds[:,0]
-df_explore['y'] = umap_embeds[:,1]
+df_explore = pd.DataFrame(data={"text": df["text"]})
+df_explore["x"] = umap_embeds[:, 0]
+df_explore["y"] = umap_embeds[:, 1]
 
 # Plot
-chart = alt.Chart(df_explore).mark_circle(size=60).encode(
-    x=#'x',
-    alt.X('x',
-        scale=alt.Scale(zero=False)
-    ),
-    y=
-    alt.Y('y',
-        scale=alt.Scale(zero=False)
-    ),
-    tooltip=['text']
-).properties(
-    width=700,
-    height=400
+chart = (
+    alt.Chart(df_explore)
+    .mark_circle(size=60)
+    .encode(
+        x=alt.X("x", scale=alt.Scale(zero=False)),  #'x',
+        y=alt.Y("y", scale=alt.Scale(zero=False)),
+        tooltip=["text"],
+    )
+    .properties(width=700, height=400)
 )
 chart.interactive()
 ```

diff --git a/fern/pages/deployment-options/cohere-on-aws/amazon-bedrock.mdx b/fern/pages/deployment-options/cohere-on-aws/amazon-bedrock.mdx
@@ -45,24 +45,29 @@ co = cohere.BedrockClient(
 )
 
 # Input parameters for embed. In this example we are embedding hacker news post titles.
-texts = ["Interesting (Non software) books?",
-         "Non-tech books that have helped you grow professionally?",
-         "I sold my company last month for $5m. What do I do with the money?",
-         "How are you getting through (and back from) burning out?",
-         "I made $24k over the last month. Now what?",
-         "What kind of personal financial investment do you do?",
-         "Should I quit the field of software development?"]
+texts = [
+    "Interesting (Non software) books?",
+    "Non-tech books that have helped you grow professionally?",
+    "I sold my company last month for $5m. What do I do with the money?",
+    "How are you getting through (and back from) burning out?",
+    "I made $24k over the last month. Now what?",
+    "What kind of personal financial investment do you do?",
+    "Should I quit the field of software development?",
+]
 input_type = "clustering"
-truncate = "NONE" # optional
-model_id = "cohere.embed-english-v3" # or "cohere.embed-multilingual-v3"
+truncate = "NONE"  # optional
+model_id = (
+    "cohere.embed-english-v3"  # or "cohere.embed-multilingual-v3"
+)
 
 
 # Invoke the model and print the response
 result = co.embed(
-						model=model_id,
-  					input_type=input_type,
-  				  texts=texts,
-  					truncate=truncate) # aws_client.invoke_model(**params)
+    model=model_id,
+    input_type=input_type,
+    texts=texts,
+    truncate=truncate,
+)  # aws_client.invoke_model(**params)
 
 print(result)
 ```
@@ -81,9 +86,10 @@ co = cohere.BedrockClient(
     aws_session_token="...",
 )
 
-result = co.chat(message="Write a LinkedIn post about starting a career in tech:",
-                 model='cohere.command-r-plus-v1:0' # or 'cohere.command-r-v1:0'
-                 )
+result = co.chat(
+    message="Write a LinkedIn post about starting a career in tech:",
+    model="cohere.command-r-plus-v1:0",  # or 'cohere.command-r-v1:0'
+)
 
 print(result)
 ```
diff --git a/fern/pages/deployment-options/cohere-on-aws/amazon-sagemaker-setup-guide.mdx b/fern/pages/deployment-options/cohere-on-aws/amazon-sagemaker-setup-guide.mdx
@@ -55,24 +55,27 @@ co = cohere.SageMakerClient(
 )
 
 # Input parameters for embed. In this example we are embedding hacker news post titles.
-texts = ["Interesting (Non software) books?",
-         "Non-tech books that have helped you grow professionally?",
-         "I sold my company last month for $5m. What do I do with the money?",
-         "How are you getting through (and back from) burning out?",
-         "I made $24k over the last month. Now what?",
-         "What kind of personal financial investment do you do?",
-         "Should I quit the field of software development?"]
+texts = [
+    "Interesting (Non software) books?",
+    "Non-tech books that have helped you grow professionally?",
+    "I sold my company last month for $5m. What do I do with the money?",
+    "How are you getting through (and back from) burning out?",
+    "I made $24k over the last month. Now what?",
+    "What kind of personal financial investment do you do?",
+    "Should I quit the field of software development?",
+]
 input_type = "clustering"
-truncate = "NONE" # optional
-model_id = "<YOUR ENDPOINT NAME>" # On SageMaker, you create a model name that you'll pass here. 
+truncate = "NONE"  # optional
+model_id = "<YOUR ENDPOINT NAME>"  # On SageMaker, you create a model name that you'll pass here.
 
 
 # Invoke the model and print the response
 result = co.embed(
-            model=model_id,
-            input_type=input_type,
-            texts=texts,
-            truncate=truncate) 
+    model=model_id,
+    input_type=input_type,
+    texts=texts,
+    truncate=truncate,
+)
 
 print(result)
 ```

diff --git a/fern/pages/deployment-options/cohere-on-microsoft-azure.mdx b/fern/pages/deployment-options/cohere-on-microsoft-azure.mdx
@@ -68,14 +68,19 @@ data = {
 body = str.encode(json.dumps(data))
 
 # Replace the url with your API endpoint
-url = "https://your-endpoint.inference.ai.azure.com/v1/chat/completions"
+url = (
+    "https://your-endpoint.inference.ai.azure.com/v1/chat/completions"
+)
 
 # Replace this with the key for the endpoint
 api_key = "your-auth-key"
 if not api_key:
     raise Exception("API Key is missing")
 
-headers = {"Content-Type": "application/json", "Authorization": (api_key)}
+headers = {
+    "Content-Type": "application/json",
+    "Authorization": (api_key),
+}
 
 req = urllib.request.Request(url, body, headers)
 
@@ -111,9 +116,7 @@ import urllib.request
 import json
 
 # Configure payload data sending to API endpoint
-data = {
-    "input": ["hi"]
-}
+data = {"input": ["hi"]}
 
 body = str.encode(json.dumps(data))
 
@@ -125,7 +128,10 @@ api_key = "your-auth-key"
 if not api_key:
     raise Exception("API Key is missing")
 
-headers = {"Content-Type": "application/json", "Authorization": (api_key)}
+headers = {
+    "Content-Type": "application/json",
+    "Authorization": (api_key),
+}
 
 req = urllib.request.Request(url, body, headers)
 
@@ -149,7 +155,7 @@ import cohere
 
 co = cohere.Client(
     base_url="https://<endpoint>.<region>.inference.ai.azure.com/v1",
-    api_key="<key>"
+    api_key="<key>",
 )
 
 documents = [
@@ -214,19 +220,19 @@ import cohere
 # For Command models
 co_chat = cohere.Client(
     api_key="AZURE_INFERENCE_CREDENTIAL",
-    base_url="AZURE_MODEL_ENDPOINT", # Example - https://Cohere-command-r-plus-08-2024-xyz.eastus.models.ai.azure.com/
+    base_url="AZURE_MODEL_ENDPOINT",  # Example - https://Cohere-command-r-plus-08-2024-xyz.eastus.models.ai.azure.com/
 )
 
 # For Embed models
 co_embed = cohere.Client(
     api_key="AZURE_INFERENCE_CREDENTIAL",
-    base_url="AZURE_MODEL_ENDPOINT", # Example - hhttps://cohere-embed-v3-multilingual-xyz.eastus.models.ai.azure.com/
+    base_url="AZURE_MODEL_ENDPOINT",  # Example - hhttps://cohere-embed-v3-multilingual-xyz.eastus.models.ai.azure.com/
 )
 
 # For Rerank models
 co_rerank = cohere.Client(
     api_key="AZURE_INFERENCE_CREDENTIAL",
-    base_url="AZURE_MODEL_ENDPOINT", # Example - hhttps://cohere-rerank-v3-multilingual-xyz.eastus.models.ai.azure.com/
+    base_url="AZURE_MODEL_ENDPOINT",  # Example - hhttps://cohere-rerank-v3-multilingual-xyz.eastus.models.ai.azure.com/
 )
 ```
 
@@ -286,7 +292,10 @@ faqs_short = [
 query = "Are there fitness-related perks?"
 
 results = co_rerank.rerank(
-    query=query, documents=faqs_short, top_n=2, model="rerank-english-v3.0"
+    query=query,
+    documents=faqs_short,
+    top_n=2,
+    model="rerank-english-v3.0",
 )
 ```
 

diff --git a/fern/pages/deployment-options/cohere-works-everywhere.mdx b/fern/pages/deployment-options/cohere-works-everywhere.mdx
@@ -192,8 +192,7 @@ const cohere = new CohereClient({
 ```python PYTHON
 import cohere
 
-co = cohere.Client(api_key="",
-                   base_url="<YOUR_DEPLOYMENT_URL>")
+co = cohere.Client(api_key="", base_url="<YOUR_DEPLOYMENT_URL>")
 
 response = co.chat(
     chat_history=[
@@ -320,7 +319,7 @@ co = cohere.BedrockClient(
 )
 
 response = co.chat(
-  	model="cohere.command-r-plus-v1:0",
+    model="cohere.command-r-plus-v1:0",
     chat_history=[
         {"role": "USER", "message": "Who discovered gravity?"},
         {
@@ -513,8 +512,8 @@ const cohere = new CohereClient({
 import cohere
 
 co = cohere.Client(
-  api_key="<azure token>",
-  base_url="https://Cohere-command-r-plus-phulf-serverless.eastus2.inference.ai.azure.com/v1",
+    api_key="<azure token>",
+    base_url="https://Cohere-command-r-plus-phulf-serverless.eastus2.inference.ai.azure.com/v1",
 )
 
 response = co.chat(