Migrate from OpenAI

Predibase supports OpenAI Chat Completions v1 compatible endpoints that makes it as easy as possible to migrate from OpenAI to Predibase.

View Colab Notebook

Steps

1. Obtain your Predibase API token
2. For the base_url, obtain your tenant ID (found on the Settings > My Profile page) and deployment name (found on the Deployments page)
3. If using a fine-tuned adapter trained on Predibase, you'll need the adapter ID ("adapter repo name"/"version number"), which is included as the model parameter when prompting.

Python SDK Example

If you fine-tuned an adapter with apply_chat_template, see the "Chat Completions" tab.

Base Model

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

completion = client.completions.create(
    model="",
    prompt="How many helicopters can a human eat in one sitting?",
    max_tokens=100,
)
print("Completion result:", completion.choices[0].text)

Fine-tuned Adapter

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
adapter = "<ADAPTER REPO NAME>/<VERSION NUMBER>" # Ex. "adapter-repo/1"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

completion = client.completions.create(
    model=adapter,
    prompt="How many helicopters can a human eat in one sitting?",
    max_tokens=100,
)
print("Completion result:", completion.choices[0].text)

Chat Completions

OpenAI Chat Completions automatically apply the chat template to your requests.

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
adapter = "<ADAPTER REPO NAME>/<VERSION NUMBER>" # Ex. "adapter-repo/1"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

content = "How many helicopters can a human eat in one sitting?"

completion = client.chat.completions.create(
    model=adapter,
    messages=[{"role": "user", "content": content}],
    max_tokens=100,
)

print("Completion result:", completion.choices[0].text)

Function Calling

OpenAI Chat Completions can also be used to call predefined tools

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
adapter = "<ADAPTER REPO NAME>/<VERSION NUMBER>" # Ex. "adapter-repo/1"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

tools = [
  {
      "type": "function",
      "function": {
          "name": "get_weather",
          "parameters": {
              "type": "object",
              "properties": {
                  "location": {"type": "string"}
              },
          },
      },
  }
]

content = "What's the weather like right now in California?"

completion = client.chat.completions.create(
    model=adapter,
    messages=[{"role": "user", "content": content}],
    max_tokens=100,
    tools=tools,
)

print("Completion result:", completion.choices[0].text)

Streaming

Base Model

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

# Prompt the base model
completion_stream = client.completions.create(
    model="",
    prompt="How many helicopters can a human eat in one sitting?",
    max_tokens=100,
    stream=True
)
text = []
for message in completion_stream:
    print(message)
    text.append(message.choices[0].text)
print("".join(text))

Fine-tuned Adapter

from openai import OpenAI

api_token = "<PREDIBASE API TOKEN>"
tenant_id = "<PREDIBASE TENANT ID>"
model_name = "<DEPLOYMENT NAME>" # Ex. "mistral-7b"
adapter = "<ADAPTER REPO NAME>/<VERSION NUMBER>" # Ex. "adapter-repo/1"
base_url = f"https://serving.app.predibase.com/{tenant_id}/deployments/v2/llms/{model_name}/v1"

client = OpenAI(
    api_key=api_token,
    base_url=base_url,
)

# Prompt the base model
completion_stream = client.completions.create(
    model=adapter,
    prompt="How many helicopters can a human eat in one sitting?",
    max_tokens=100,
    stream=True
)
response = []
for message in completion_stream:
    token = message.choices[0].text
    response.append(token)
    print(token, end='')
print("".join(response))

REST API Example

export PREDIBASE_API_TOKEN="<YOUR TOKEN HERE>"
export PREDIBASE_ENDPOINT="<YOUR ENDPOINT HERE>"
#PREDIBASE_ENDPOINT_EXAMPLE: https://serving.app.predibase.com/{tenantID}/deployments/v2/llms/mistral-7b-instruct

curl -i $PREDIBASE_ENDPOINT/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${PREDIBASE_API_TOKEN}" \
  -d '{"model": "", "messages": [{ "role": "user", "content": "How many helicopters can a human eat in one sitting?"}],"max_tokens": 100}'