importoutlinesfromenumimportEnumfrompydanticimportBaseModelfromtransformersimportAutoTokenizer,AutoModelForCausalLMfromtypingimportListMODEL_NAME="microsoft/Phi-3-mini-4k-instruct"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))defalert_manager(ticket):print("Alert!",ticket)classTicketPriority(str,Enum):low="low"medium="medium"high="high"urgent="urgent"classServiceTicket(BaseModel):priority:TicketPrioritycategory:strrequires_manager:boolsummary:straction_items:List[str]customer_email="""Subject: URGENT - Cannot access my account after paymentI paid for the premium plan 3 hours ago and still can't access any features.I've tried logging out and back in multiple times. This is unacceptable as Ihave a client presentation in an hour and need the analytics dashboard.Please fix this immediately or refund my payment."""prompt=f"""<|im_start|>userAnalyze this customer email:{customer_email}<|im_end|><|im_start|>assistant"""ticket=model(prompt,ServiceTicket,max_new_tokens=500)# Use structured data to route the ticketticket=ServiceTicket.model_validate_json(ticket)ifticket.priority=="urgent"orticket.requires_manager:alert_manager(ticket)

importoutlinesfrompydanticimportBaseModelfromtransformersimportAutoTokenizer,AutoModelForCausalLMfromtypingimportList,OptionalMODEL_NAME="microsoft/Phi-3-mini-4k-instruct"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))defupdate_inventory(product,category,sub_category):print(f"Updated{product.split(',')[0]} in category{category}/{sub_category}")classProductCategory(BaseModel):main_category:strsub_category:strattributes:List[str]brand_match:Optional[str]# Process product descriptions in batchesproduct_descriptions= ["Apple iPhone 15 Pro Max 256GB Titanium, 6.7-inch Super Retina XDR display with ProMotion","Organic Cotton T-Shirt, Men's Medium, Navy Blue, 100% Sustainable Materials","KitchenAid Stand Mixer, 5 Quart, Red, 10-Speed Settings with Dough Hook Attachment"]template=outlines.Template.from_string("""<|im_start|>userCategorize this product:{{ description }}<|im_end|><|im_start|>assistant""")# Get structured categorization for all productscategories=model(    [template(description=desc)fordescinproduct_descriptions],ProductCategory,max_new_tokens=200)# Use categorization for inventory managementcategories= [ProductCategory.model_validate_json(category)forcategoryincategories]forproduct,categoryinzip(product_descriptions,categories):update_inventory(product,category.main_category,category.sub_category)

importoutlinesfromtypingimportUnion,List,LiteralfrompydanticimportBaseModelfromenumimportEnumfromtransformersimportAutoTokenizer,AutoModelForCausalLMMODEL_NAME="microsoft/Phi-3-mini-4k-instruct"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))classEventType(str,Enum):conference="conference"webinar="webinar"workshop="workshop"meetup="meetup"other="other"classEventInfo(BaseModel):"""Structured information about a tech event"""name:strdate:strlocation:strevent_type:EventTypetopics:List[str]registration_required:bool# Create a union type that can either be a structured EventInfo or "I don't know"EventResponse=Union[EventInfo,Literal["I don't know"]]# Sample event descriptionsevent_descriptions= [# Complete information"""    Join us for DevCon 2023, the premier developer conference happening on November 15-17, 2023    at the San Francisco Convention Center. Topics include AI/ML, cloud infrastructure, and web3.    Registration is required.    """,# Insufficient information"""    Tech event next week. More details coming soon!    """]# Process eventsresults= []fordescriptioninevent_descriptions:prompt=f"""<|im_start>systemYou are a helpful assistant<|im_end|><|im_start>userExtract structured information about this tech event:{description}If there is enough information, return a JSON object with the following fields:- name: The name of the event- date: The date where the event is taking place- location: Where the event is taking place- event_type: either 'conference', 'webinar', 'workshop', 'meetup' or 'other'- topics: a list of topics of the conference- registration_required: a boolean that indicates whether registration is requiredIf the information available does not allow you to fill this JSON, and only then, answer 'I don't know'.<|im_end|><|im_start|>assistant"""# Union type allows the model to return structured data or "I don't know"result=model(prompt,EventResponse,max_new_tokens=200)results.append(result)# Display resultsfori,resultinenumerate(results):print(f"Event{i+1}:")ifisinstance(result,str):print(f"{result}")else:# It's an EventInfo objectprint(f"  Name:{result.name}")print(f"  Type:{result.event_type}")print(f"  Date:{result.date}")print(f"  Topics:{', '.join(result.topics)}")print()# Use structured data in downstream processingstructured_count=sum(1forrinresultsifisinstance(r,EventInfo))print(f"Successfully extracted data for{structured_count} of{len(results)} events")

importoutlinesfromtypingimportLiteral,ListimportpandasaspdfromtransformersimportAutoTokenizer,AutoModelForCausalLMMODEL_NAME="microsoft/Phi-3-mini-4k-instruct"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))# Define classification categories using LiteralDocumentCategory=Literal["Financial Report","Legal Contract","Technical Documentation","Marketing Material","Personal Correspondence"]# Sample documents to classifydocuments= ["Q3 Financial Summary: Revenue increased by 15% year-over-year to $12.4M. EBITDA margin improved to 23% compared to 19% in Q3 last year. Operating expenses...","This agreement is made between Party A and Party B, hereinafter referred to as 'the Parties', on this day of...","The API accepts POST requests with JSON payloads. Required parameters include 'user_id' and 'transaction_type'. The endpoint returns a 200 status code on success."]template=outlines.Template.from_string("""<|im_start|>userClassify the following document into exactly one category among the following categories:- Financial Report- Legal Contract- Technical Documentation- Marketing Material- Personal CorrespondenceDocument:{{ document }}<|im_end|><|im_start|>assistant""")# Classify documentsdefclassify_documents(texts:List[str])->List[DocumentCategory]:results= []fortextintexts:prompt=template(document=text)# The model must return one of the predefined categoriescategory=model(prompt,DocumentCategory,max_new_tokens=200)results.append(category)returnresults# Perform classificationclassifications=classify_documents(documents)# Create a simple results tableresults_df=pd.DataFrame({"Document": [doc[:50]+"..."fordocindocuments],"Classification":classifications})print(results_df)# Count documents by categorycategory_counts=pd.Series(classifications).value_counts()print("\nCategory Distribution:")print(category_counts)

importoutlinesimportjsonfromtypingimportList,OptionalfromdatetimeimportdatefromtransformersimportAutoTokenizer,AutoModelForCausalLMMODEL_NAME="microsoft/phi-4"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))# Define a function with typed parametersdefschedule_meeting(title:str,date:date,duration_minutes:int,attendees:List[str],location:Optional[str]=None,agenda_items:Optional[List[str]]=None):"""Schedule a meeting with the specified details"""# In a real app, this would create the meetingmeeting= {"title":title,"date":date,"duration_minutes":duration_minutes,"attendees":attendees,"location":location,"agenda_items":agenda_items    }returnf"Meeting '{title}' scheduled for{date} with{len(attendees)} attendees"# Natural language requestuser_request="""I need to set up a product roadmap review with the engineering team for nextTuesday at 2pm. It should last 90 minutes. Please invite john@example.com,sarah@example.com, and the product team at product@example.com."""# Outlines automatically infers the required structure from the function signatureprompt=f"""<|im_start|>userExtract the meeting details from this request:{user_request}<|im_end|><|im_start|>assistant"""meeting_params=model(prompt,schedule_meeting,max_new_tokens=200)# The result is a dictionary matching the function parametersmeeting_params=json.loads(meeting_params)print(meeting_params)# Call the function with the extracted parametersresult=schedule_meeting(**meeting_params)print(result)# "Meeting 'Product Roadmap Review' scheduled for 2023-10-17 with 3 attendees"

importoutlinesfromtypingimportList,LiteralfromtransformersimportAutoTokenizer,AutoModelForCausalLMMODEL_NAME="microsoft/phi-4"model=outlines.from_transformers(AutoModelForCausalLM.from_pretrained(MODEL_NAME,device_map="auto"),AutoTokenizer.from_pretrained(MODEL_NAME))# 1. Create a reusable template with Jinja syntaxsentiment_template=outlines.Template.from_string("""<|im_start>userAnalyze the sentiment of the following {{ content_type }}:{{ text }}Provide your analysis as either "Positive", "Negative", or "Neutral".<|im_end><|im_start>assistant""")# 2. Generate prompts with different parametersreview="This restaurant exceeded all my expectations. Fantastic service!"prompt=sentiment_template(content_type="review",text=review)# 3. Use the templated prompt with structured generationresult=model(prompt,Literal["Positive","Negative","Neutral"])print(result)# "Positive"# Templates can also be loaded from filesexample_template=outlines.Template.from_file("templates/few_shot.txt")# Use with examples for few-shot learningexamples= [    ("The food was cold","Negative"),    ("The staff was friendly","Positive")]few_shot_prompt=example_template(examples=examples,query="Service was slow")print(few_shot_prompt)