Cohere v2 Python
Overview
Cohere's v2 Chat API provides powerful conversational AI capabilities with a specialized focus on structured outputs through JSON Schema mode. This skill covers entity extraction, data validation, and integration patterns for building production-ready systems that require consistent, validated responses from LLMs.
When to Use This Skill
Apply this skill when:
- Extracting structured entities from unstructured text (names, dates, locations, organizations)
- Building Named Entity Recognition (NER) systems
- Implementing data extraction pipelines with validated outputs
- Requiring JSON responses that conform to specific schemas
- Processing documents for information extraction
- Building classification systems with constrained outputs
- Integrating LLM responses with downstream databases or APIs
Core Capabilities
1. Basic Chat API
Initialize and use the Cohere Client for conversational tasks:
import cohere
co = cohere.ClientV2(api_key="<YOUR API KEY>")
response = co.chat(
model="command-a-03-2025",
messages=[
{"role": "user", "content": "Summarize the key features of quantum computing."}
],
)
print(response.message.content[0].text)
Available models:
command-a-03-2025- Latest generation model
For comprehensive API parameters, streaming, RAG, and tool use, refer to references/chat_api.md.
2. Entity Extraction with JSON Schema Mode
The primary strength of Cohere v2 is structured outputs using JSON Schema mode, which guarantees responses conform to your specified schema.
Simple Entity Extraction:
text = "Dr. Sarah Johnson from Stanford University will speak at the AI Conference in Seattle on March 15th."
response = co.chat(
model="command-a-03-2025",
messages=[
{"role": "user", "content": f"Extract all entities: {text}"}
],
response_format={
"type": "json_object",
"schema": {
"type": "object",
"properties": {
"person": {"type": "string"},
"title": {"type": "string"},
"organization": {"type": "string"},
"event": {"type": "string"},
"location": {"type": "string"},
"date": {"type": "string", "format": "date"}
},
"required": ["person"]
}
}
)
import json
entities = json.loads(response.message.content[0].text)
Key Principles:
- Top-level type must be
"object" - At least one field must be in
"required"array - Schema is strictly enforced - invalid responses are regenerated
- First request has latency overhead; subsequent requests are cached
3. Multiple Entity Extraction
Extract arrays of entities for batch processing:
text = """
John Smith works at Google as a Software Engineer in San Francisco.
Jane Doe is a Data Scientist at Meta in New York.
Bob Wilson leads the AI team at OpenAI in Seattle.
"""
response = co.chat(
model="command-a-03-2025",
messages=[
{"role": "user", "content": f"Extract all people and their details: {text}"}
],
response_format={
"type": "json_object",
"schema": {
"type": "object",
"properties": {
"people": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {"type": "string"},
"company": {"type": "string"},
"role": {"type": "string"},
"location": {"type": "string"}
},
"required": ["name", "company"]
}
}
},
"required": ["people"]
}
}
)
result = json.loads(response.message.content[0].text)
for person in result["people"]:
print(f"{person['name']} works at {person['company']}")
4. Classification with Enums
Use enums to constrain outputs to specific categories:
text = "I absolutely love this product! The quality is amazing and customer service was helpful."
response = co.chat(
model="command-a-03-2025",
messages=[
{"role": "user", "content": f"Analyze sentiment and aspects: {text}"}
],
response_format={
"type": "json_object",
"schema": {
"type": "object",
"properties": {
"overall_sentiment": {
"type": "string",
"enum": ["positive", "negative", "neutral", "mixed"]
},
"aspects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"aspect": {"type": "string"},
"sentiment": {
"type": "string",
"enum": ["positive", "negative", "neutral"]
}
},
"required": ["aspect", "sentiment"]
}
}
},
"required": ["overall_sentiment", "aspects"]
}
}
)
Benefits of Enums:
- Guarantees valid category values
- Eliminates post-processing validation
- Enables direct database insertion
- Supports downstream logic without error handling
Common Entity Extraction Patterns
Named Entity Recognition (NER)
schema = {
"type": "object",
"properties": {
"entities": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {"type": "string"},
"type": {
"type": "string",
"enum": ["PERSON", "ORGANIZATION", "LOCATION", "DATE", "EVENT", "PRODUCT"]
},
"context": {"type": "string"}
},
"required": ["text", "type"]
}
}
},
"required": ["entities"]
}
Resume/CV Parsing
schema = {
"type": "object",
"properties": {
"name": {"type": "string"},
"email": {
"type": "string",
"pattern": "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$"
},
"phone": {"type": "string"},
"experience": {
"type": "array",
"items": {
"type": "object",
"properties": {
"company": {"type": "string"},
"role": {"type": "string"},
"start_date": {"type": "string", "format": "date"},
"end_date": {"type": "string", "format": "date"},
"description": {"type": "string"}
},
"required": ["company", "role"]
}
},
"education": {
"type": "array",
"items": {
"type": "object",
"properties": {
"institution": {"type": "string"},
"degree": {"type": "string"},
"field": {"type": "string"},
"graduation_year": {"type": "integer"}
},
"required": ["institution"]
}
},
"skills": {
"type": "array",
"items": {"type": "string"}
}
},
"required": ["name"]
}
Invoice/Receipt Extraction
schema = {
"type": "object",
"properties": {
"invoice_number": {"type": "string"},
"invoice_date": {"type": "string", "format": "date"},
"vendor": {
"type": "object",
"properties": {
"name": {"type": "string"},
"address": {"type": "string"},