[AUR-385, AUR-388] Declare BaseComponent and decide LLM call interface (#2)
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873
- Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`:
```python
from kotaemon.llms.chats.openai import AzureChatOpenAI
model = AzureChatOpenAI(
openai_api_base="https://test.openai.azure.com/",
openai_api_key="some-key",
openai_api_version="2023-03-15-preview",
deployment_name="gpt35turbo",
temperature=0,
request_timeout=60,
)
output = model("hello world")
```
For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow:
- Completion LLM component:
```python
class CompletionLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run text completion: str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run text completion in batch: list[str] in -> list[LLMInterface] out
# run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case
```
- Chat LLM component:
```python
class ChatLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run chat completion (no chat history): str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out
def run_document(self, text: list[BaseMessage]) -> LLMInterface:
# Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out
def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]:
# Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out
```
- The LLMInterface is as follow:
```python
@dataclass
class LLMInterface:
text: list[str]
completion_tokens: int = -1
total_tokens: int = -1
prompt_tokens: int = -1
logits: list[list[float]] = field(default_factory=list)
```
2023-08-29 15:47:12 +07:00
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
2023-08-30 07:22:01 +07:00
|
|
|
from langchain.llms import AzureOpenAI as AzureOpenAILC
|
|
|
|
|
from langchain.llms import OpenAI as OpenAILC
|
[AUR-385, AUR-388] Declare BaseComponent and decide LLM call interface (#2)
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873
- Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`:
```python
from kotaemon.llms.chats.openai import AzureChatOpenAI
model = AzureChatOpenAI(
openai_api_base="https://test.openai.azure.com/",
openai_api_key="some-key",
openai_api_version="2023-03-15-preview",
deployment_name="gpt35turbo",
temperature=0,
request_timeout=60,
)
output = model("hello world")
```
For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow:
- Completion LLM component:
```python
class CompletionLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run text completion: str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run text completion in batch: list[str] in -> list[LLMInterface] out
# run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case
```
- Chat LLM component:
```python
class ChatLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run chat completion (no chat history): str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out
def run_document(self, text: list[BaseMessage]) -> LLMInterface:
# Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out
def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]:
# Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out
```
- The LLMInterface is as follow:
```python
@dataclass
class LLMInterface:
text: list[str]
completion_tokens: int = -1
total_tokens: int = -1
prompt_tokens: int = -1
logits: list[list[float]] = field(default_factory=list)
```
2023-08-29 15:47:12 +07:00
|
|
|
|
|
|
|
|
from kotaemon.llms.base import LLMInterface
|
2023-08-30 07:22:01 +07:00
|
|
|
from kotaemon.llms.completions.openai import AzureOpenAI, OpenAI
|
[AUR-385, AUR-388] Declare BaseComponent and decide LLM call interface (#2)
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873
- Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`:
```python
from kotaemon.llms.chats.openai import AzureChatOpenAI
model = AzureChatOpenAI(
openai_api_base="https://test.openai.azure.com/",
openai_api_key="some-key",
openai_api_version="2023-03-15-preview",
deployment_name="gpt35turbo",
temperature=0,
request_timeout=60,
)
output = model("hello world")
```
For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow:
- Completion LLM component:
```python
class CompletionLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run text completion: str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run text completion in batch: list[str] in -> list[LLMInterface] out
# run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case
```
- Chat LLM component:
```python
class ChatLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run chat completion (no chat history): str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out
def run_document(self, text: list[BaseMessage]) -> LLMInterface:
# Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out
def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]:
# Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out
```
- The LLMInterface is as follow:
```python
@dataclass
class LLMInterface:
text: list[str]
completion_tokens: int = -1
total_tokens: int = -1
prompt_tokens: int = -1
logits: list[list[float]] = field(default_factory=list)
```
2023-08-29 15:47:12 +07:00
|
|
|
|
|
|
|
|
_openai_completion_response = {
|
|
|
|
|
"id": "cmpl-7qyNoIo6gRSCJR0hi8o3ZKBH4RkJ0",
|
|
|
|
|
"object": "sample text_completion",
|
|
|
|
|
"created": 1392751226,
|
|
|
|
|
"model": "gpt-35-turbo",
|
|
|
|
|
"choices": [
|
|
|
|
|
{"text": "completion", "index": 0, "finish_reason": "length", "logprobs": None}
|
|
|
|
|
],
|
|
|
|
|
"usage": {"completion_tokens": 20, "prompt_tokens": 2, "total_tokens": 22},
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@patch(
|
|
|
|
|
"openai.api_resources.completion.Completion.create",
|
|
|
|
|
side_effect=lambda *args, **kwargs: _openai_completion_response,
|
|
|
|
|
)
|
|
|
|
|
def test_azureopenai_model(openai_completion):
|
|
|
|
|
model = AzureOpenAI(
|
|
|
|
|
openai_api_base="https://test.openai.azure.com/",
|
|
|
|
|
openai_api_key="some-key",
|
|
|
|
|
openai_api_version="2023-03-15-preview",
|
|
|
|
|
deployment_name="gpt35turbo",
|
|
|
|
|
temperature=0,
|
|
|
|
|
request_timeout=60,
|
|
|
|
|
)
|
|
|
|
|
assert isinstance(
|
|
|
|
|
model.agent, AzureOpenAILC
|
|
|
|
|
), "Agent not wrapped in Langchain's AzureOpenAI"
|
|
|
|
|
|
|
|
|
|
output = model(["hello world"])
|
|
|
|
|
assert isinstance(output, list), "Output for batch is not a list"
|
|
|
|
|
assert isinstance(output[0], LLMInterface), "Output for text is not LLMInterface"
|
|
|
|
|
openai_completion.assert_called()
|
|
|
|
|
|
|
|
|
|
output = model("hello world")
|
2023-08-30 07:22:01 +07:00
|
|
|
assert isinstance(
|
|
|
|
|
output, LLMInterface
|
|
|
|
|
), "Output for single text is not LLMInterface"
|
[AUR-385, AUR-388] Declare BaseComponent and decide LLM call interface (#2)
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873
- Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`:
```python
from kotaemon.llms.chats.openai import AzureChatOpenAI
model = AzureChatOpenAI(
openai_api_base="https://test.openai.azure.com/",
openai_api_key="some-key",
openai_api_version="2023-03-15-preview",
deployment_name="gpt35turbo",
temperature=0,
request_timeout=60,
)
output = model("hello world")
```
For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow:
- Completion LLM component:
```python
class CompletionLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run text completion: str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run text completion in batch: list[str] in -> list[LLMInterface] out
# run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case
```
- Chat LLM component:
```python
class ChatLLM:
def run_raw(self, text: str) -> LLMInterface:
# Run chat completion (no chat history): str in -> LLMInterface out
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
# Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out
def run_document(self, text: list[BaseMessage]) -> LLMInterface:
# Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out
def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]:
# Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out
```
- The LLMInterface is as follow:
```python
@dataclass
class LLMInterface:
text: list[str]
completion_tokens: int = -1
total_tokens: int = -1
prompt_tokens: int = -1
logits: list[list[float]] = field(default_factory=list)
```
2023-08-29 15:47:12 +07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
@patch(
|
|
|
|
|
"openai.api_resources.completion.Completion.create",
|
|
|
|
|
side_effect=lambda *args, **kwargs: _openai_completion_response,
|
|
|
|
|
)
|
|
|
|
|
def test_openai_model(openai_completion):
|
|
|
|
|
model = OpenAI(
|
|
|
|
|
openai_api_base="https://test.openai.azure.com/",
|
|
|
|
|
openai_api_key="some-key",
|
|
|
|
|
openai_api_version="2023-03-15-preview",
|
|
|
|
|
deployment_name="gpt35turbo",
|
|
|
|
|
temperature=0,
|
|
|
|
|
request_timeout=60,
|
|
|
|
|
)
|
|
|
|
|
assert isinstance(
|
|
|
|
|
model.agent, OpenAILC
|
|
|
|
|
), "Agent is not wrapped in Langchain's OpenAI"
|
|
|
|
|
|
|
|
|
|
output = model(["hello world"])
|
|
|
|
|
assert isinstance(output, list), "Output for batch is not a list"
|
|
|
|
|
assert isinstance(output[0], LLMInterface), "Output for text is not LLMInterface"
|
|
|
|
|
openai_completion.assert_called()
|
|
|
|
|
|
|
|
|
|
output = model("hello world")
|
2023-08-30 07:22:01 +07:00
|
|
|
assert isinstance(
|
|
|
|
|
output, LLMInterface
|
|
|
|
|
), "Output for single text is not LLMInterface"
|