Merge pull request #2432 from danielaskdd/embedding-example
Doc: Update README examples to prevent double-wrapping of embedding functions
This commit is contained in:
Daniel.y
GitHub
commit
1b02684e2f
3 changed files with 69 additions and 43 deletions
55
README-zh.md
55
README-zh.md
|
|
@ -407,6 +407,11 @@ LightRAG 需要利用LLM和Embeding模型来完成文档索引和知识库查询
|
|||
* LightRAG还支持类OpenAI的聊天/嵌入API：
|
||||
|
||||
```python
|
||||
import os
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
|
||||
|
||||
async def llm_model_func(
|
||||
prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
|
||||
) -> str:
|
||||
|
|
@ -420,8 +425,9 @@ async def llm_model_func(
|
|||
**kwargs
|
||||
)
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=4096, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await openai_embed(
|
||||
return await openai_embed.func(
|
||||
texts,
|
||||
model="solar-embedding-1-large-query",
|
||||
api_key=os.getenv("UPSTAGE_API_KEY"),
|
||||
|
|
@ -432,16 +438,17 @@ async def initialize_rag():
|
|||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=llm_model_func,
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=4096,
|
||||
func=embedding_func
|
||||
)
|
||||
embedding_func=embedding_func # 直接传入装饰后的函数
|
||||
)
|
||||
|
||||
await rag.initialize_storages()
|
||||
return rag
|
||||
```
|
||||
|
||||
> **关于嵌入函数封装的重要说明：**
|
||||
>
|
||||
> `EmbeddingFunc` 不能嵌套封装。已经被 `@wrap_embedding_func_with_attrs` 装饰过的嵌入函数（如 `openai_embed`、`ollama_embed` 等）不能再次使用 `EmbeddingFunc()` 封装。这就是为什么在创建自定义嵌入函数时，我们调用 `xxx_embed.func`（底层未封装的函数）而不是直接调用 `xxx_embed`。
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
|
@ -478,19 +485,20 @@ rag = LightRAG(
|
|||
然后您只需要按如下方式设置LightRAG：
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.ollama import ollama_model_complete, ollama_embed
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=768, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await ollama_embed.func(texts, embed_model="nomic-embed-text")
|
||||
|
||||
# 使用Ollama模型初始化LightRAG
|
||||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=ollama_model_complete, # 使用Ollama模型进行文本生成
|
||||
llm_model_name='your_model_name', # 您的模型名称
|
||||
# 使用Ollama嵌入函数
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=768,
|
||||
func=lambda texts: ollama_embed(
|
||||
texts,
|
||||
embed_model="nomic-embed-text"
|
||||
)
|
||||
),
|
||||
embedding_func=embedding_func, # 直接传入装饰后的函数
|
||||
)
|
||||
```
|
||||
|
||||
|
|
@ -529,22 +537,27 @@ ollama create -f Modelfile qwen2m
|
|||
您可以使用`llm_model_kwargs`参数配置ollama：
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.ollama import ollama_model_complete, ollama_embed
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=768, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await ollama_embed.func(texts, embed_model="nomic-embed-text")
|
||||
|
||||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=ollama_model_complete, # 使用Ollama模型进行文本生成
|
||||
llm_model_name='your_model_name', # 您的模型名称
|
||||
llm_model_kwargs={"options": {"num_ctx": 32768}},
|
||||
# 使用Ollama嵌入函数
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=768,
|
||||
func=lambda texts: ollama_embed(
|
||||
texts,
|
||||
embed_model="nomic-embed-text"
|
||||
)
|
||||
),
|
||||
embedding_func=embedding_func, # 直接传入装饰后的函数
|
||||
)
|
||||
```
|
||||
|
||||
> **关于嵌入函数封装的重要说明：**
|
||||
>
|
||||
> `EmbeddingFunc` 不能嵌套封装。已经被 `@wrap_embedding_func_with_attrs` 装饰过的嵌入函数（如 `openai_embed`、`ollama_embed` 等）不能再次使用 `EmbeddingFunc()` 封装。这就是为什么在创建自定义嵌入函数时，我们调用 `xxx_embed.func`（底层未封装的函数）而不是直接调用 `xxx_embed`。
|
||||
|
||||
* **低RAM GPU**
|
||||
|
||||
为了在低RAM GPU上运行此实验，您应该选择小型模型并调整上下文窗口（增加上下文会增加内存消耗）。例如，在6Gb RAM的改装挖矿GPU上运行这个ollama示例需要将上下文大小设置为26k，同时使用`gemma2:2b`。它能够在`book.txt`中找到197个实体和19个关系。
|
||||
|
|
|
|||
55
README.md
55
README.md
|
|
@ -403,6 +403,11 @@ LightRAG requires the utilization of LLM and Embedding models to accomplish docu
|
|||
* LightRAG also supports Open AI-like chat/embeddings APIs:
|
||||
|
||||
```python
|
||||
import os
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.openai import openai_complete_if_cache, openai_embed
|
||||
|
||||
async def llm_model_func(
|
||||
prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
|
||||
) -> str:
|
||||
|
|
@ -416,8 +421,9 @@ async def llm_model_func(
|
|||
**kwargs
|
||||
)
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=4096, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await openai_embed(
|
||||
return await openai_embed.func(
|
||||
texts,
|
||||
model="solar-embedding-1-large-query",
|
||||
api_key=os.getenv("UPSTAGE_API_KEY"),
|
||||
|
|
@ -428,16 +434,17 @@ async def initialize_rag():
|
|||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=llm_model_func,
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=4096,
|
||||
func=embedding_func
|
||||
)
|
||||
embedding_func=embedding_func # Pass the decorated function directly
|
||||
)
|
||||
|
||||
await rag.initialize_storages()
|
||||
return rag
|
||||
```
|
||||
|
||||
> **Important Note on Embedding Function Wrapping:**
|
||||
>
|
||||
> `EmbeddingFunc` cannot be nested. Functions that have been decorated with `@wrap_embedding_func_with_attrs` (such as `openai_embed`, `ollama_embed`, etc.) cannot be wrapped again using `EmbeddingFunc()`. This is why we call `xxx_embed.func` (the underlying unwrapped function) instead of `xxx_embed` directly when creating custom embedding functions.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
|
@ -476,19 +483,20 @@ If you want to use Ollama models, you need to pull model you plan to use and emb
|
|||
Then you only need to set LightRAG as follows:
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.ollama import ollama_model_complete, ollama_embed
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=768, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await ollama_embed.func(texts, embed_model="nomic-embed-text")
|
||||
|
||||
# Initialize LightRAG with Ollama model
|
||||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=ollama_model_complete, # Use Ollama model for text generation
|
||||
llm_model_name='your_model_name', # Your model name
|
||||
# Use Ollama embedding function
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=768,
|
||||
func=lambda texts: ollama_embed(
|
||||
texts,
|
||||
embed_model="nomic-embed-text"
|
||||
)
|
||||
),
|
||||
embedding_func=embedding_func, # Pass the decorated function directly
|
||||
)
|
||||
```
|
||||
|
||||
|
|
@ -527,22 +535,27 @@ ollama create -f Modelfile qwen2m
|
|||
Tiy can use `llm_model_kwargs` param to configure ollama:
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
from lightrag.utils import wrap_embedding_func_with_attrs
|
||||
from lightrag.llm.ollama import ollama_model_complete, ollama_embed
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=768, max_token_size=8192)
|
||||
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||||
return await ollama_embed.func(texts, embed_model="nomic-embed-text")
|
||||
|
||||
rag = LightRAG(
|
||||
working_dir=WORKING_DIR,
|
||||
llm_model_func=ollama_model_complete, # Use Ollama model for text generation
|
||||
llm_model_name='your_model_name', # Your model name
|
||||
llm_model_kwargs={"options": {"num_ctx": 32768}},
|
||||
# Use Ollama embedding function
|
||||
embedding_func=EmbeddingFunc(
|
||||
embedding_dim=768,
|
||||
func=lambda texts: ollama_embed(
|
||||
texts,
|
||||
embed_model="nomic-embed-text"
|
||||
)
|
||||
),
|
||||
embedding_func=embedding_func, # Pass the decorated function directly
|
||||
)
|
||||
```
|
||||
|
||||
> **Important Note on Embedding Function Wrapping:**
|
||||
>
|
||||
> `EmbeddingFunc` cannot be nested. Functions that have been decorated with `@wrap_embedding_func_with_attrs` (such as `openai_embed`, `ollama_embed`, etc.) cannot be wrapped again using `EmbeddingFunc()`. This is why we call `xxx_embed.func` (the underlying unwrapped function) instead of `xxx_embed` directly when creating custom embedding functions.
|
||||
|
||||
* **Low RAM GPUs**
|
||||
|
||||
In order to run this experiment on low RAM GPU you should select small model and tune context window (increasing context increase memory consumption). For example, running this ollama example on repurposed mining GPU with 6Gb of RAM required to set context size to 26k while using `gemma2:2b`. It was able to find 197 entities and 19 relations on `book.txt`.
|
||||
|
|
|
|||
|
|
@ -867,7 +867,7 @@ async def azure_openai_complete(
|
|||
return result
|
||||
|
||||
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=1536)
|
||||
@wrap_embedding_func_with_attrs(embedding_dim=1536, max_token_size=8192)
|
||||
async def azure_openai_embed(
|
||||
texts: list[str],
|
||||
model: str | None = None,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue