Separated llms from the main llm.py file and fixed some deprication bugs

examples/insert_custom_kg.py

@@ -1,6 +1,6 @@
 import os
 from lightrag import LightRAG
-from lightrag.llm import gpt_4o_mini_complete
+from lightrag.llm.openai import gpt_4o_mini_complete
 #########
 # Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert()
 # import nest_asyncio

examples/lightrag_api_ollama_demo.py

@@ -2,7 +2,7 @@ from fastapi import FastAPI, HTTPException, File, UploadFile
 from pydantic import BaseModel
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_embedding, ollama_model_complete
+from lightrag.llm.ollama import ollama_embed, ollama_model_complete
 from lightrag.utils import EmbeddingFunc
 from typing import Optional
 import asyncio
@@ -38,7 +38,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=768,
         max_token_size=8192,
-        func=lambda texts: ollama_embedding(
+        func=lambda texts: ollama_embed(
             texts, embed_model="nomic-embed-text", host="http://localhost:11434"
         ),
     ),

examples/lightrag_api_open_webui_demo.py

@@ -9,7 +9,7 @@ from typing import Optional
 import os
 import logging
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_model_complete, ollama_embed
+from lightrag.llm.ollama import ollama_model_complete, ollama_embed
 from lightrag.utils import EmbeddingFunc
 
 import nest_asyncio

examples/lightrag_api_openai_compatible_demo.py

@@ -2,7 +2,7 @@ from fastapi import FastAPI, HTTPException, File, UploadFile
 from pydantic import BaseModel
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 from typing import Optional
@@ -48,7 +48,7 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model=EMBEDDING_MODEL,
     )

examples/lightrag_api_oracle_demo.py

@@ -13,7 +13,7 @@ from pathlib import Path
 import asyncio
 import nest_asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 
@@ -64,7 +64,7 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model=EMBEDDING_MODEL,
         api_key=APIKEY,

examples/lightrag_bedrock_demo.py

@@ -6,7 +6,7 @@ import os
 import logging
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import bedrock_complete, bedrock_embedding
+from lightrag.llm.bedrock import bedrock_complete, bedrock_embed
 from lightrag.utils import EmbeddingFunc
 
 logging.getLogger("aiobotocore").setLevel(logging.WARNING)
@@ -20,7 +20,7 @@ rag = LightRAG(
     llm_model_func=bedrock_complete,
     llm_model_name="Anthropic Claude 3 Haiku // Amazon Bedrock",
     embedding_func=EmbeddingFunc(
-        embedding_dim=1024, max_token_size=8192, func=bedrock_embedding
+        embedding_dim=1024, max_token_size=8192, func=bedrock_embed
     ),
 )
 

examples/lightrag_hf_demo.py

@@ -1,7 +1,7 @@
 import os
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import hf_model_complete, hf_embedding
+from lightrag.llm.hf import hf_model_complete, hf_embed
 from lightrag.utils import EmbeddingFunc
 from transformers import AutoModel, AutoTokenizer
 
@@ -17,7 +17,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=384,
         max_token_size=5000,
-        func=lambda texts: hf_embedding(
+        func=lambda texts: hf_embed(
             texts,
             tokenizer=AutoTokenizer.from_pretrained(
                 "sentence-transformers/all-MiniLM-L6-v2"

examples/lightrag_jinaai_demo.py

@@ -1,13 +1,14 @@
 import numpy as np
 from lightrag import LightRAG, QueryParam
 from lightrag.utils import EmbeddingFunc
-from lightrag.llm import jina_embedding, openai_complete_if_cache
+from lightrag.llm.jina import jina_embed
+from lightrag.llm.openai import openai_complete_if_cache
 import os
 import asyncio
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await jina_embedding(texts, api_key="YourJinaAPIKey")
+    return await jina_embed(texts, api_key="YourJinaAPIKey")
 
 
 WORKING_DIR = "./dickens"

examples/lightrag_lmdeploy_demo.py

@@ -1,7 +1,8 @@
 import os
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import lmdeploy_model_if_cache, hf_embedding
+from lightrag.llm.lmdeploy import lmdeploy_model_if_cache
+from lightrag.llm.hf import hf_embed
 from lightrag.utils import EmbeddingFunc
 from transformers import AutoModel, AutoTokenizer
 
@@ -42,7 +43,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=384,
         max_token_size=5000,
-        func=lambda texts: hf_embedding(
+        func=lambda texts: hf_embed(
             texts,
             tokenizer=AutoTokenizer.from_pretrained(
                 "sentence-transformers/all-MiniLM-L6-v2"

examples/lightrag_nvidia_demo.py

@@ -3,7 +3,7 @@ import asyncio
 from lightrag import LightRAG, QueryParam
 from lightrag.llm import (
     openai_complete_if_cache,
-    nvidia_openai_embedding,
+    nvidia_openai_embed,
 )
 from lightrag.utils import EmbeddingFunc
 import numpy as np
@@ -47,7 +47,7 @@ nvidia_embed_model = "nvidia/nv-embedqa-e5-v5"
 
 
 async def indexing_embedding_func(texts: list[str]) -> np.ndarray:
-    return await nvidia_openai_embedding(
+    return await nvidia_openai_embed(
         texts,
         model=nvidia_embed_model,  # maximum 512 token
         # model="nvidia/llama-3.2-nv-embedqa-1b-v1",
@@ -60,7 +60,7 @@ async def indexing_embedding_func(texts: list[str]) -> np.ndarray:
 
 
 async def query_embedding_func(texts: list[str]) -> np.ndarray:
-    return await nvidia_openai_embedding(
+    return await nvidia_openai_embed(
         texts,
         model=nvidia_embed_model,  # maximum 512 token
         # model="nvidia/llama-3.2-nv-embedqa-1b-v1",

examples/lightrag_ollama_age_demo.py

@@ -4,7 +4,7 @@ import logging
 import os
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_embedding, ollama_model_complete
+from lightrag.llm.ollama import ollama_embed, ollama_model_complete
 from lightrag.utils import EmbeddingFunc
 
 WORKING_DIR = "./dickens_age"
@@ -32,7 +32,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=768,
         max_token_size=8192,
-        func=lambda texts: ollama_embedding(
+        func=lambda texts: ollama_embed(
             texts, embed_model="nomic-embed-text", host="http://localhost:11434"
         ),
     ),

examples/lightrag_ollama_demo.py

@@ -3,7 +3,7 @@ import os
 import inspect
 import logging
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_model_complete, ollama_embedding
+from lightrag.llm.ollama import ollama_model_complete, ollama_embed
 from lightrag.utils import EmbeddingFunc
 
 WORKING_DIR = "./dickens"
@@ -23,7 +23,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=768,
         max_token_size=8192,
-        func=lambda texts: ollama_embedding(
+        func=lambda texts: ollama_embed(
             texts, embed_model="nomic-embed-text", host="http://localhost:11434"
         ),
     ),

examples/lightrag_ollama_gremlin_demo.py

@@ -10,7 +10,7 @@ import os
 # logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.WARN)
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_embedding, ollama_model_complete
+from lightrag.llm.ollama import ollama_embed, ollama_model_complete
 from lightrag.utils import EmbeddingFunc
 
 WORKING_DIR = "./dickens_gremlin"
@@ -41,7 +41,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=768,
         max_token_size=8192,
-        func=lambda texts: ollama_embedding(
+        func=lambda texts: ollama_embed(
             texts, embed_model="nomic-embed-text", host="http://localhost:11434"
         ),
     ),

examples/lightrag_ollama_neo4j_milvus_mongo_demo.py

@@ -1,6 +1,6 @@
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_model_complete, ollama_embed
+from lightrag.llm.ollama import ollama_model_complete, ollama_embed
 from lightrag.utils import EmbeddingFunc
 
 # WorkingDir

examples/lightrag_openai_compatible_demo.py

@@ -1,7 +1,7 @@
 import os
 import asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 
@@ -26,7 +26,7 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model="solar-embedding-1-large-query",
         api_key=os.getenv("UPSTAGE_API_KEY"),

examples/lightrag_openai_compatible_demo_embedding_cache.py

@@ -1,7 +1,7 @@
 import os
 import asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 
@@ -26,7 +26,7 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model="solar-embedding-1-large-query",
         api_key=os.getenv("UPSTAGE_API_KEY"),

examples/lightrag_openai_compatible_stream_demo.py

@@ -1,7 +1,7 @@
 import os
 import inspect
 from lightrag import LightRAG
-from lightrag.llm import openai_complete, openai_embedding
+from lightrag.llm import openai_complete, openai_embed
 from lightrag.utils import EmbeddingFunc
 from lightrag.lightrag import always_get_an_event_loop
 from lightrag import QueryParam
@@ -24,7 +24,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=1024,
         max_token_size=8192,
-        func=lambda texts: openai_embedding(
+        func=lambda texts: openai_embed(
             texts=texts,
             model="text-embedding-bge-m3",
             base_url="http://127.0.0.1:1234/v1",

examples/lightrag_openai_demo.py

@@ -1,7 +1,7 @@
 import os
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import gpt_4o_mini_complete
+from lightrag.llm.openai import gpt_4o_mini_complete
 
 WORKING_DIR = "./dickens"
 

examples/lightrag_openai_neo4j_milvus_redis_demo.py

@@ -1,6 +1,6 @@
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_embed, openai_complete_if_cache
+from lightrag.llm.ollama import ollama_embed, openai_complete_if_cache
 from lightrag.utils import EmbeddingFunc
 
 # WorkingDir

examples/lightrag_oracle_demo.py

@@ -3,7 +3,7 @@ import os
 from pathlib import Path
 import asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 from lightrag.kg.oracle_impl import OracleDB
@@ -42,7 +42,7 @@ async def llm_model_func(
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model=EMBEDMODEL,
         api_key=APIKEY,

examples/lightrag_siliconcloud_demo.py

@@ -1,7 +1,8 @@
 import os
 import asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import openai_complete_if_cache, siliconcloud_embedding
+from lightrag.llm.openai import openai_complete_if_cache
+from lightrag.llm.siliconcloud import siliconcloud_embedding
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 

examples/lightrag_zhipu_demo.py

@@ -3,7 +3,7 @@ import logging
 
 
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import zhipu_complete, zhipu_embedding
+from lightrag.llm.zhipu import zhipu_complete, zhipu_embedding
 from lightrag.utils import EmbeddingFunc
 
 WORKING_DIR = "./dickens"

examples/lightrag_zhipu_postgres_demo.py

@@ -6,7 +6,7 @@ from dotenv import load_dotenv
 
 from lightrag import LightRAG, QueryParam
 from lightrag.kg.postgres_impl import PostgreSQLDB
-from lightrag.llm import ollama_embedding, zhipu_complete
+from lightrag.llm.zhipu import ollama_embedding, zhipu_complete
 from lightrag.utils import EmbeddingFunc
 
 load_dotenv()

examples/test.py

@@ -1,6 +1,6 @@
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import gpt_4o_mini_complete
+from lightrag.llm.openai import gpt_4o_mini_complete
 #########
 # Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert()
 # import nest_asyncio

examples/test_chromadb.py

@@ -1,7 +1,7 @@
 import os
 import asyncio
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import gpt_4o_mini_complete, openai_embedding
+from lightrag.llm.openai import gpt_4o_mini_complete, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
 
@@ -35,7 +35,7 @@ EMBEDDING_MAX_TOKEN_SIZE = int(os.environ.get("EMBEDDING_MAX_TOKEN_SIZE", 8192))
 
 
 async def embedding_func(texts: list[str]) -> np.ndarray:
-    return await openai_embedding(
+    return await openai_embed(
         texts,
         model=EMBEDDING_MODEL,
     )

examples/test_neo4j.py

@@ -1,6 +1,6 @@
 import os
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import gpt_4o_mini_complete
+from lightrag.llm.openai import gpt_4o_mini_complete
 
 
 #########

examples/test_split_by_character.ipynb

@@ -16,7 +16,7 @@
     "import logging\n",
     "import numpy as np\n",
     "from lightrag import LightRAG, QueryParam\n",
-    "from lightrag.llm import openai_complete_if_cache, openai_embedding\n",
+    "from lightrag.llm.openai import openai_complete_if_cache, openai_embed\n",
     "from lightrag.utils import EmbeddingFunc\n",
     "import nest_asyncio"
    ]
@@ -74,7 +74,7 @@
     "\n",
     "\n",
     "async def embedding_func(texts: list[str]) -> np.ndarray:\n",
-    "    return await openai_embedding(\n",
+    "    return await openai_embed(\n",
     "        texts,\n",
     "        model=\"ep-20241231173413-pgjmk\",\n",
     "        api_key=API,\n",
@@ -138,7 +138,7 @@
     "\n",
     "\n",
     "async def embedding_func(texts: list[str]) -> np.ndarray:\n",
-    "    return await openai_embedding(\n",
+    "    return await openai_embed(\n",
     "        texts,\n",
     "        model=\"ep-20241231173413-pgjmk\",\n",
     "        api_key=API,\n",

examples/vram_management_demo.py

@@ -1,7 +1,7 @@
 import os
 import time
 from lightrag import LightRAG, QueryParam
-from lightrag.llm import ollama_model_complete, ollama_embedding
+from lightrag.llm.ollama import ollama_model_complete, ollama_embed
 from lightrag.utils import EmbeddingFunc
 
 # Working directory and the directory path for text files
@@ -20,7 +20,7 @@ rag = LightRAG(
     embedding_func=EmbeddingFunc(
         embedding_dim=768,
         max_token_size=8192,
-        func=lambda texts: ollama_embedding(texts, embed_model="nomic-embed-text"),
+        func=lambda texts: ollama_embed(texts, embed_model="nomic-embed-text"),
     ),
 )