examples
**Code Examples and Templates**
**LLM API Quick Start Templates**
**OpenAI Chat Completion**
```python
from openai import OpenAI
client = OpenAI() # Uses OPENAI_API_KEY env var
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
],
max_tokens=500,
temperature=0.7,
)
print(response.choices[0].message.content)
```
**Anthropic Claude**
```python
from anthropic import Anthropic
client = Anthropic() # Uses ANTHROPIC_API_KEY env var
response = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello, Claude!"}
]
)
print(response.content[0].text)
```
**Streaming Response**
```python
**OpenAI**
stream = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Write a haiku."}],
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
```
**Hugging Face Transformers (Local)**
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype="auto"
)
messages = [{"role": "user", "content": "What is the capital of France?"}]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
**RAG Template**
```python
from openai import OpenAI
import chromadb
**Setup**
client = OpenAI()
chroma = chromadb.Client()
collection = chroma.create_collection("docs")
**Add documents**
docs = ["Document 1 content...", "Document 2 content..."]
collection.add(
documents=docs,
ids=[f"doc_{i}" for i in range(len(docs))]
)
**Query**
def rag_query(question: str, n_results: int = 3):
results = collection.query(query_texts=[question], n_results=n_results)
context = "
".join(results["documents"][0])
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": f"Answer based on context:
{context}"},
{"role": "user", "content": question}
]
)
return response.choices[0].message.content
print(rag_query("What does document 1 say?"))
```
**Project Structure Template**
```svg
```