Add langchain_llm package

Author: xusenlin

libs/langchain_llm/README.md

@@ -0,0 +1,105 @@
+# Langchain LLM
+
+## Get Started
+
+### Install
+
+```shell
+pip install langchain_llm
+```
+
+## Inference Usage
+
+### HuggingFace Inference
+
+**Completion Usage**
+
+```python
+from langchain_llm import HuggingFaceLLM
+
+llm = HuggingFaceLLM(
+    model_name="qwen-7b-chat",
+    model_path="/data/checkpoints/Qwen-7B-Chat",
+    load_model_kwargs={"device_map": "auto"},
+)
+
+# invoke method
+prompt = "<|im_start|>user\n你是谁？<|im_end|>\n<|im_start|>assistant\n"
+print(llm.invoke(prompt, stop=["<|im_end|>"]))
+
+# Token Streaming
+for chunk in llm.stream(prompt, stop=["<|im_end|>"]):
+    print(chunk, end="", flush=True)
+
+# openai usage
+print(llm.call_as_openai(prompt, stop=["<|im_end|>"]))
+
+# Streaming
+for chunk in llm.call_as_openai(prompt, stop=["<|im_end|>"], stream=True):
+    print(chunk.choices[0].text, end="", flush=True)
+```
+
+**Chat Completion Usage**
+
+```python
+from langchain_llm import ChatHuggingFace
+
+chat_llm = ChatHuggingFace(llm=llm)
+
+# invoke method
+query = "你是谁？"
+print(chat_llm.invoke(query))
+
+# Token Streaming
+for chunk in chat_llm.stream(query):
+    print(chunk.content, end="", flush=True)
+
+# openai usage
+messages = [
+    {"role": "user", "content": query}
+]
+print(chat_llm.call_as_openai(messages))
+
+# Streaming
+for chunk in chat_llm.call_as_openai(messages, stream=True):
+    print(chunk.choices[0].delta.content or "", end="", flush=True)
+```
+
+### VLLM Inference
+
+**Completion Usage**
+
+```python
+from langchain_llm import VLLM
+
+llm = VLLM(
+    model_name="qwen", 
+    model="/data/checkpoints/Qwen-7B-Chat", 
+    trust_remote_code=True,
+)
+
+# invoke method
+prompt = "<|im_start|>user\n你是谁？<|im_end|>\n<|im_start|>assistant\n"
+print(llm.invoke(prompt, stop=["<|im_end|>"]))
+
+# openai usage
+print(llm.call_as_openai(prompt, stop=["<|im_end|>"]))
+```
+
+**Chat Completion Usage**
+
+```python
+from langchain_llm import ChatVLLM
+
+chat_llm = ChatVLLM(llm=llm)
+
+# invoke method
+query = "你是谁？"
+print(chat_llm.invoke(query))
+
+# openai usage
+messages = [
+    {"role": "user", "content": query}
+]
+print(chat_llm.call_as_openai(messages))
+```

libs/langchain_llm/langchain_llm/__init__.py

@@ -0,0 +1,14 @@
+from ._huggingface import (
+    HuggingFaceLLM,
+    ChatHuggingFace,
+)
+from ._vllm import XVLLM as VLLM
+from ._vllm import ChatVLLM
+
+
+__all__ = [
+    "HuggingFaceLLM",
+    "ChatHuggingFace",
+    "VLLM",
+    "ChatVLLM",
+]

libs/langchain_llm/langchain_llm/_compat.py

@@ -0,0 +1,36 @@
+from __future__ import annotations
+
+from typing import Any, cast, Dict, Type
+
+import pydantic
+
+# --------------- Pydantic v2 compatibility ---------------
+
+PYDANTIC_V2 = pydantic.VERSION.startswith("2.")
+
+
+def model_json(model: pydantic.BaseModel, **kwargs) -> str:
+    if PYDANTIC_V2:
+        return model.model_dump_json(**kwargs)
+    return model.json(**kwargs)  # type: ignore
+
+
+def model_dump(model: pydantic.BaseModel, **kwargs) -> Dict[str, Any]:
+    if PYDANTIC_V2:
+        return model.model_dump(**kwargs)
+    return cast(
+        "dict[str, Any]",
+        model.dict(**kwargs),
+    )
+
+
+def model_parse(model: Type[pydantic.BaseModel], data: Any) -> pydantic.BaseModel:
+    if PYDANTIC_V2:
+        return model.model_validate(data)
+    return model.parse_obj(data)  # pyright: ignore[reportDeprecated]
+
+
+def disable_warnings(model: Type[pydantic.BaseModel]):
+    # Disable warning for model_name settings
+    if PYDANTIC_V2:
+        model.model_config["protected_namespaces"] = ()