Skip to content

Upgrade foundational models #277

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

Merged
preritdas merged 7 commits into from
Dec 28, 2025
Merged

Upgrade foundational models #277

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7b650df
Use GPT-5 Mini for many insights generation.
preritdas Dec 28, 2025
db486b8
Use GPT-5 Mini for per-lead insights.
preritdas Dec 28, 2025
d89951c
Use GPT-5 Mini for FUB AI mapping.
preritdas Dec 28, 2025
e4a09a2
Remove `max_tokens=` parameter as no longer supported.
preritdas Dec 28, 2025
31cc077
Remove outdated API parameters.
preritdas Dec 28, 2025
67bb81e
Remove `.beta` on OpenAI client.
preritdas Dec 28, 2025
0d7014c
Upgrade OpenAI SDK.
preritdas Dec 28, 2025
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
16 changes: 4 additions & 12 deletions real_intent/analyze/insights/many.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,8 +81,8 @@ def _analyze(self, pii_md5s: list[MD5WithPII]) -> str:

@retry_with_backoff()
def generate_insights():
return self.openai_client.beta.chat.completions.parse(
model="gpt-4o-mini",
return self.openai_client.chat.completions.parse(
model="gpt-5-mini",
messages=[
{
"role": "system",
Expand All @@ -93,11 +93,7 @@ def generate_insights():
"content": csv_data
}
],
max_tokens=4095,
temperature=1,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
response_format=LeadInsights
)

Expand Down Expand Up @@ -257,8 +253,8 @@ def _analyze(self, pii_md5s: list[MD5WithPII]) -> str:

@retry_with_backoff()
def generate_insights():
return self.openai_client.beta.chat.completions.parse(
model="gpt-4o-mini",
return self.openai_client.chat.completions.parse(
model="gpt-5-mini",
messages=[
{
"role": "system",
Expand All @@ -273,11 +269,7 @@ def generate_insights():
)
}
],
max_tokens=4095,
temperature=1,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
response_format=ValidatedLeadInsights
)

Expand Down
8 changes: 2 additions & 6 deletions real_intent/analyze/insights/per_lead.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,8 @@ def _analyze_one(self, pii_md5: MD5WithPII) -> LeadInsight:

@retry_with_backoff()
def generate_insight():
return self.openai_client.beta.chat.completions.parse(
model="gpt-4o-mini",
return self.openai_client.chat.completions.parse(
model="gpt-5-mini",
messages=[
{
"role": "system",
Expand All @@ -105,11 +105,7 @@ def generate_insight():
)
}
],
max_tokens=2000,
temperature=1,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
response_format=LeadInsight
)

Expand Down
6 changes: 1 addition & 5 deletions real_intent/deliver/followupboss/ai_fields.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,7 +278,7 @@ def _prepare_event_data(self, md5_with_pii: MD5WithPII) -> dict:
# Match the custom fields with the PII data
log("debug", "Sending request to OpenAI for field mapping")
response = self.openai_client.chat.completions.create(
model="gpt-4.1-mini",
model="gpt-5-mini",
messages=[
{
"role": "system",
Expand All @@ -292,11 +292,7 @@ def _prepare_event_data(self, md5_with_pii: MD5WithPII) -> dict:
)
}
],
max_tokens=4095,
temperature=0.7,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
response_format={"type": "json_object"}
)

Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ pandas
requests

logfire>=3.16.2
openai==1.97.0
openai==2.14.0
reportlab>=4.4.2

python-dotenv
Expand Down