通过API将 Ollama 集成到Python应用程序中 REST

curl http://localhost:11434/api/chat -d '{
  "model": "qwen3.5:9b",
  "messages": [{"role": "user", "content": "Bonjour"}],
  "stream": false
}'

curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5:9b",
    "messages": [{"role": "user", "content": "Bonjour"}]
  }'

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama",  # ignoré, mais requis par le SDK
)

reponse = client.chat.completions.create(
    model="qwen3.5:9b",
    messages=[
        {"role": "system", "content": "Tu réponds en français, de façon concise."},
        {"role": "user", "content": "Explique en une phrase ce qu'est un LLM."},
    ],
    temperature=0.3,
)

print(reponse.choices[0].message.content)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

flux = client.chat.completions.create(
    model="qwen3.5:9b",
    messages=[{"role": "user", "content": "Raconte une courte histoire de robot."}],
    stream=True,
)

for chunk in flux:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)
print()

from openai import OpenAI
import json

client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

reponse = client.chat.completions.create(
    model="qwen3.5:9b",
    messages=[
        {"role": "system", "content": (
            "Tu extrais des informations structurées. "
            "Réponds uniquement avec un objet JSON contenant les clés : "
            "nom (string), age (int), ville (string)."
        )},
        {"role": "user", "content": "Marie a 34 ans, elle habite à Lyon."},
    ],
    response_format={"type": "json_object"},
    temperature=0,
)

donnees = json.loads(reponse.choices[0].message.content)
print(donnees)
# {'nom': 'Marie', 'age': 34, 'ville': 'Lyon'}

from openai import OpenAI
import json

client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

# 1. Une fonction Python réelle
def meteo(ville: str) -> dict:
    # En vrai, vous appelleriez Open-Meteo ou autre
    return {"ville": ville, "temperature_c": 18, "conditions": "nuageux"}

# 2. Sa description au format OpenAI
outils = [{
    "type": "function",
    "function": {
        "name": "meteo",
        "description": "Donne la météo actuelle d'une ville française.",
        "parameters": {
            "type": "object",
            "properties": {
                "ville": {"type": "string", "description": "Nom de la ville"},
            },
            "required": ["ville"],
        },
    },
}]

messages = [{"role": "user", "content": "Quel temps fait-il à Bordeaux ?"}]

# 3. Premier appel : le modèle décide d'appeler la fonction
reponse = client.chat.completions.create(
    model="qwen3.5:9b",
    messages=messages,
    tools=outils,
)

appel = reponse.choices[0].message.tool_calls[0]
args = json.loads(appel.function.arguments)
resultat = meteo(**args)

# 4. Second appel : on renvoie le résultat au modèle pour la réponse finale
messages.append(reponse.choices[0].message)
messages.append({
    "role": "tool",
    "tool_call_id": appel.id,
    "content": json.dumps(resultat),
})

finale = client.chat.completions.create(model="qwen3.5:9b", messages=messages)
print(finale.choices[0].message.content)

pip install fastapi uvicorn openai

from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from openai import OpenAI

app = FastAPI()
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

class Question(BaseModel):
    message: str
    model: str = "qwen3.5:9b"

@app.post("/chat")
def chat(q: Question):
    reponse = client.chat.completions.create(
        model=q.model,
        messages=[{"role": "user", "content": q.message}],
    )
    return {"reponse": reponse.choices[0].message.content}

@app.post("/chat/stream")
def chat_stream(q: Question):
    def generateur():
        flux = client.chat.completions.create(
            model=q.model,
            messages=[{"role": "user", "content": q.message}],
            stream=True,
        )
        for chunk in flux:
            delta = chunk.choices[0].delta.content
            if delta:
                yield delta
    return StreamingResponse(generateur(), media_type="text/plain")

uvicorn main:app --reload --port 8000

curl -N -X POST http://localhost:8000/chat/stream \
  -H "Content-Type: application/json" \
  -d '{"message": "Écris un haïku sur Paris."}'

pip install flask openai

from flask import Flask, request, jsonify, Response
from openai import OpenAI
from collections import defaultdict

app = Flask(__name__)
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

# Historiques par session — en prod : Redis, Postgres, etc.
historiques: dict[str, list] = defaultdict(lambda: [
    {"role": "system", "content": "Tu es un assistant en français, concis et utile."},
])

@app.post("/chat/<session_id>")
def chat(session_id: str):
    message = request.json["message"]
    historique = historiques[session_id]
    historique.append({"role": "user", "content": message})

    reponse = client.chat.completions.create(
        model="qwen3.5:9b",
        messages=historique,
    )
    contenu = reponse.choices[0].message.content
    historique.append({"role": "assistant", "content": contenu})
    return jsonify({"reponse": contenu})

@app.post("/chat/<session_id>/stream")
def chat_stream(session_id: str):
    message = request.json["message"]
    historique = historiques[session_id]
    historique.append({"role": "user", "content": message})

    def generateur():
        morceaux = []
        flux = client.chat.completions.create(
            model="qwen3.5:9b",
            messages=historique,
            stream=True,
        )
        for chunk in flux:
            delta = chunk.choices[0].delta.content
            if delta:
                morceaux.append(delta)
                yield delta
        historique.append({"role": "assistant", "content": "".join(morceaux)})

    return Response(generateur(), mimetype="text/plain")

@app.delete("/chat/<session_id>")
def reset(session_id: str):
    historiques.pop(session_id, None)
    return "", 204

if __name__ == "__main__":
    app.run(port=5000, debug=True)

有反馈、发现了错误，或想补充说明？请告诉我们，让这份指南对每个人都更有帮助。