Skip to content

Fix response content handling in text generation tutorial #798

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Rishabh-k-Paliwal wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix response content handling in text generation tutorial #798

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
05ea461
Fix response content handling in text generation tutorial
Rishabh-k-Paliwal Aug 25, 2026
96b3cc4
Fix streaming response content handling
Rishabh-k-Paliwal Aug 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 34 additions & 13 deletions fern/pages/v2/tutorials/build-things-with-cohere/text-generation-tutorial.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,6 @@ co = cohere.ClientV2(api_key="COHERE_API_KEY")

To get started with Chat, we need to pass two parameters, `model` for the LLM model ID and `messages`, which we add a single user message. We then call the Chat endpoint through the client we created earlier.

The response contains several objects. For simplicity, what we want right now is the `message.content[0].text` object.

Here's an example of the assistant responding to a new hire's query asking for help to make introductions.


Expand All @@ -60,7 +58,11 @@ response = co.chat(
)
# messages=[cohere.UserMessage(content=message)])

print(response.message.content[0].text)
for content_item in response.message.content:
if content_item.type == "thinking":
print("thinking:", content_item.thinking)
if content_item.type == "text":
print("text:", content_item.text)
```

```
Expand Down Expand Up @@ -103,7 +105,11 @@ response = co.chat(
)
# messages=[cohere.UserMessage(content=message)])

print(response.message.content[0].text)
for content_item in response.message.content:
if content_item.type == "thinking":
print("thinking:", content_item.thinking)
if content_item.type == "text":
print("text:", content_item.text)
```

```
Expand Down Expand Up @@ -144,7 +150,11 @@ response = co.chat(
messages=[{"role": "user", "content": message}],
)

print(response.message.content[0].text)
for content_item in response.message.content:
if content_item.type == "thinking":
print("thinking:", content_item.thinking)
if content_item.type == "text":
print("text:", content_item.text)
```

```
Expand Down Expand Up @@ -173,7 +183,11 @@ response = co.chat(
messages=[{"role": "user", "content": message}],
)

print(response.message.content[0].text)
for content_item in response.message.content:
if content_item.type == "thinking":
print("thinking:", content_item.thinking)
if content_item.type == "text":
print("text:", content_item.text)
```

```
Expand Down Expand Up @@ -201,7 +215,9 @@ for idx in range(3):
temperature=0,
)

print(f"{idx+1}: {response.message.content[0].text}\n")
for content_item in response.message.content:
if content_item.type == "text":
print(f"{idx+1}: {content_item.text}\n")
```

```
Expand All @@ -228,7 +244,9 @@ for idx in range(3):
temperature=1,
)

print(f"{idx+1}: {response.message.content[0].text}\n")
for content_item in response.message.content:
if content_item.type == "text":
print(f"{idx+1}: {content_item.text}\n")
```

```
Expand Down Expand Up @@ -293,7 +311,10 @@ response = co.chat(
},
)

json_object = json.loads(response.message.content[0].text)
for content_item in response.message.content:
if content_item.type == "text":
json_object = json.loads(content_item.text)
break

print(json_object)
```
Expand All @@ -314,7 +335,7 @@ The Chat endpoint also provides streaming support. In a streamed response, the e

To activate it, use `co.chat_stream()` instead of `co.chat()`.

In streaming mode, the endpoint will generate a series of objects. To get the actual text contents, we take objects whose `event_type` is `content-delta`.
In streaming mode, the endpoint will generate a series of objects. To get the actual text contents, we take objects whose `event.type` is `content-delta`.


```python PYTHON
Expand All @@ -328,9 +349,9 @@ response = co.chat_stream(
)

for event in response:
if event:
if event.type == "content-delta":
print(event.delta.message.content.text, end="")
if event and event.type == "content-delta":
if event.delta.message.content.text:
print(event.delta.message.content.text, end="", flush=True)
```

```
Expand Down