github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-09-04 16:51:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Upgrade to LlamaIndex to 0.10 (#1663)

Browse Source 
* Extract optional dependencies

* Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity

* Support Ollama embeddings

* Upgrade to llamaindex 0.10.14. Remove legacy use of ServiceContext in ContextChatEngine

* Fix vector retriever filters
This commit is contained in:
Iván Martínez
2024-03-06 17:51:30 +01:00
committed by GitHub
parent 12f3a39e8a
commit 45f05711eb
43 changed files with 1474 additions and 1396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
private_gpt/components/llm/custom/sagemaker.py
View File

@@ -7,26 +7,20 @@ import logging
from typing import TYPE_CHECKING, Any
import boto3 # type: ignore
from llama_index.bridge.pydantic import Field
from llama_index.llms import (
from llama_index.core.base.llms.generic_utils import (
completion_response_to_chat_response,
stream_completion_response_to_chat_response,
)
from llama_index.core.bridge.pydantic import Field
from llama_index.core.llms import (
CompletionResponse,
CustomLLM,
LLMMetadata,
)
from llama_index.llms.base import (
from llama_index.core.llms.callbacks import (
llm_chat_callback,
llm_completion_callback,
)
from llama_index.llms.generic_utils import (
completion_response_to_chat_response,
stream_completion_response_to_chat_response,
)
from llama_index.llms.llama_utils import (
completion_to_prompt as generic_completion_to_prompt,
)
from llama_index.llms.llama_utils import (
messages_to_prompt as generic_messages_to_prompt,
)
if TYPE_CHECKING:
from collections.abc import Sequence
@@ -161,8 +155,8 @@ class SagemakerLLM(CustomLLM):
model_kwargs = model_kwargs or {}
model_kwargs.update({"n_ctx": context_window, "verbose": verbose})
messages_to_prompt = messages_to_prompt or generic_messages_to_prompt
completion_to_prompt = completion_to_prompt or generic_completion_to_prompt
messages_to_prompt = messages_to_prompt or {}
completion_to_prompt = completion_to_prompt or {}
generate_kwargs = generate_kwargs or {}
generate_kwargs.update(

54
private_gpt/components/llm/llm_component.py
View File

@@ -1,9 +1,9 @@
import logging
from injector import inject, singleton
from llama_index import set_global_tokenizer
from llama_index.llms import MockLLM
from llama_index.llms.base import LLM
from llama_index.core.llms import LLM, MockLLM
from llama_index.core.settings import Settings as LlamaIndexSettings
from llama_index.core.utils import set_global_tokenizer
from transformers import AutoTokenizer # type: ignore
from private_gpt.components.llm.prompt_helper import get_prompt_style
@@ -30,17 +30,23 @@ class LLMComponent:
logger.info("Initializing the LLM in mode=%s", llm_mode)
match settings.llm.mode:
case "local":
from llama_index.llms import LlamaCPP
case "llamacpp":
try:
from llama_index.llms.llama_cpp import LlamaCPP # type: ignore
except ImportError as e:
raise ImportError(
"Local dependencies not found, install with `poetry install --extras llms-llama-cpp`"
) from e
prompt_style = get_prompt_style(settings.local.prompt_style)
prompt_style = get_prompt_style(settings.llamacpp.prompt_style)
self.llm = LlamaCPP(
model_path=str(models_path / settings.local.llm_hf_model_file),
model_path=str(models_path / settings.llamacpp.llm_hf_model_file),
temperature=0.1,
max_new_tokens=settings.llm.max_new_tokens,
context_window=settings.llm.context_window,
generate_kwargs={},
callback_manager=LlamaIndexSettings.callback_manager,
# All to GPU
model_kwargs={"n_gpu_layers": -1, "offload_kqv": True},
# transform inputs into Llama2 format
@@ -50,7 +56,12 @@ class LLMComponent:
)
case "sagemaker":
from private_gpt.components.llm.custom.sagemaker import SagemakerLLM
try:
from private_gpt.components.llm.custom.sagemaker import SagemakerLLM
except ImportError as e:
raise ImportError(
"Sagemaker dependencies not found, install with `poetry install --extras llms-sagemaker`"
) from e
self.llm = SagemakerLLM(
endpoint_name=settings.sagemaker.llm_endpoint_name,
@@ -58,7 +69,12 @@ class LLMComponent:
context_window=settings.llm.context_window,
)
case "openai":
from llama_index.llms import OpenAI
try:
from llama_index.llms.openai import OpenAI # type: ignore
except ImportError as e:
raise ImportError(
"OpenAI dependencies not found, install with `poetry install --extras llms-openai`"
) from e
openai_settings = settings.openai
self.llm = OpenAI(
@@ -67,7 +83,12 @@ class LLMComponent:
model=openai_settings.model,
)
case "openailike":
from llama_index.llms import OpenAILike
try:
from llama_index.llms.openai_like import OpenAILike # type: ignore
except ImportError as e:
raise ImportError(
"OpenAILike dependencies not found, install with `poetry install --extras llms-openai-like`"
) from e
openai_settings = settings.openai
self.llm = OpenAILike(
@@ -78,12 +99,17 @@ class LLMComponent:
max_tokens=None,
api_version="",
)
case "mock":
self.llm = MockLLM()
case "ollama":
from llama_index.llms import Ollama
try:
from llama_index.llms.ollama import Ollama # type: ignore
except ImportError as e:
raise ImportError(
"Ollama dependencies not found, install with `poetry install --extras llms-ollama`"
) from e
ollama_settings = settings.ollama
self.llm = Ollama(
model=ollama_settings.model, base_url=ollama_settings.api_base
model=ollama_settings.llm_model, base_url=ollama_settings.api_base
)
case "mock":
self.llm = MockLLM()

64
private_gpt/components/llm/prompt_helper.py
View File

@@ -3,11 +3,7 @@ import logging
from collections.abc import Sequence
from typing import Any, Literal
from llama_index.llms import ChatMessage, MessageRole
from llama_index.llms.llama_utils import (
completion_to_prompt,
messages_to_prompt,
)
from llama_index.core.llms import ChatMessage, MessageRole
logger = logging.getLogger(__name__)
@@ -73,7 +69,9 @@ class DefaultPromptStyle(AbstractPromptStyle):
class Llama2PromptStyle(AbstractPromptStyle):
"""Simple prompt style that just uses the default llama_utils functions.
"""Simple prompt style that uses llama 2 prompt style.
Inspired by llama_index/legacy/llms/llama_utils.py
It transforms the sequence of messages into a prompt that should look like:
```text
@@ -83,11 +81,61 @@ class Llama2PromptStyle(AbstractPromptStyle):
```
"""
BOS, EOS = "<s>", "</s>"
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
DEFAULT_SYSTEM_PROMPT = """\
You are a helpful, respectful and honest assistant. \
Always answer as helpfully as possible and follow ALL given instructions. \
Do not speculate or make up information. \
Do not reference any given instructions or context. \
"""
def _messages_to_prompt(self, messages: Sequence[ChatMessage]) -> str:
return messages_to_prompt(messages)
string_messages: list[str] = []
if messages[0].role == MessageRole.SYSTEM:
# pull out the system message (if it exists in messages)
system_message_str = messages[0].content or ""
messages = messages[1:]
else:
system_message_str = self.DEFAULT_SYSTEM_PROMPT
system_message_str = f"{self.B_SYS} {system_message_str.strip()} {self.E_SYS}"
for i in range(0, len(messages), 2):
# first message should always be a user
user_message = messages[i]
assert user_message.role == MessageRole.USER
if i == 0:
# make sure system prompt is included at the start
str_message = f"{self.BOS} {self.B_INST} {system_message_str} "
else:
# end previous user-assistant interaction
string_messages[-1] += f" {self.EOS}"
# no need to include system prompt
str_message = f"{self.BOS} {self.B_INST} "
# include user message content
str_message += f"{user_message.content} {self.E_INST}"
if len(messages) > (i + 1):
# if assistant message exists, add to str_message
assistant_message = messages[i + 1]
assert assistant_message.role == MessageRole.ASSISTANT
str_message += f" {assistant_message.content}"
string_messages.append(str_message)
return "".join(string_messages)
def _completion_to_prompt(self, completion: str) -> str:
return completion_to_prompt(completion)
system_prompt_str = self.DEFAULT_SYSTEM_PROMPT
return (
f"{self.BOS} {self.B_INST} {self.B_SYS} {system_prompt_str.strip()} {self.E_SYS} "
f"{completion.strip()} {self.E_INST}"
)
class TagPromptStyle(AbstractPromptStyle):