remove tqdm and cleaned readme and ollama

lightrag/kg/faiss_impl.py

@@ -22,7 +22,6 @@ if not pm.is_installed("faiss"):
 
 try:
     import faiss
-    from tqdm.asyncio import tqdm as tqdm_async
 except ImportError as e:
     raise ImportError(
         "`faiss` library is not installed. Please install it via pip: `pip install faiss`."
@@ -109,16 +108,7 @@ class FaissVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        pbar = tqdm_async(
-            total=len(batches), desc="Generating embeddings", unit="batch"
-        )
-
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
 
         # Flatten the list of arrays

lightrag/kg/milvus_impl.py

@@ -1,7 +1,6 @@
 import asyncio
 import os
 from typing import Any, final
-from tqdm.asyncio import tqdm as tqdm_async
 from dataclasses import dataclass
 import numpy as np
 from lightrag.utils import logger
@@ -94,15 +93,7 @@ class MilvusVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
-        pbar = tqdm_async(
-            total=len(embedding_tasks), desc="Generating embeddings", unit="batch"
-        )
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
 
         embeddings = np.concatenate(embeddings_list)

lightrag/kg/mongo_impl.py

@@ -2,7 +2,6 @@ import os
 from dataclasses import dataclass
 import numpy as np
 import configparser
-from tqdm.asyncio import tqdm as tqdm_async
 import asyncio
 
 from typing import Any, List, Union, final
@@ -854,17 +853,8 @@ class MongoVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
-        pbar = tqdm_async(
-            total=len(embedding_tasks), desc="Generating embeddings", unit="batch"
-        )
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
-
         embeddings = np.concatenate(embeddings_list)
         for i, d in enumerate(list_data):
             d["vector"] = np.array(embeddings[i], dtype=np.float32).tolist()

lightrag/kg/nano_vector_db_impl.py

@@ -1,7 +1,6 @@
 import asyncio
 import os
 from typing import Any, final
-from tqdm.asyncio import tqdm as tqdm_async
 from dataclasses import dataclass
 import numpy as np
 
@@ -71,15 +70,7 @@ class NanoVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
-        pbar = tqdm_async(
-            total=len(embedding_tasks), desc="Generating embeddings", unit="batch"
-        )
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
 
         embeddings = np.concatenate(embeddings_list)

lightrag/kg/postgres_impl.py

@@ -41,7 +41,6 @@ if not pm.is_installed("asyncpg"):
 
 try:
     import asyncpg
-    from tqdm.asyncio import tqdm as tqdm_async
 
 except ImportError as e:
     raise ImportError(
@@ -380,15 +379,7 @@ class PGVectorStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
-        pbar = tqdm_async(
-            total=len(embedding_tasks), desc="Generating embeddings", unit="batch"
-        )
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
 
         embeddings = np.concatenate(embeddings_list)

lightrag/kg/qdrant_impl.py

@@ -1,7 +1,6 @@
 import asyncio
 import os
 from typing import Any, final
-from tqdm.asyncio import tqdm as tqdm_async
 from dataclasses import dataclass
 import numpy as np
 import hashlib
@@ -110,15 +109,7 @@ class QdrantVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
 
-        async def wrapped_task(batch):
-            result = await self.embedding_func(batch)
-            pbar.update(1)
-            return result
-
-        embedding_tasks = [wrapped_task(batch) for batch in batches]
-        pbar = tqdm_async(
-            total=len(embedding_tasks), desc="Generating embeddings", unit="batch"
-        )
+        embedding_tasks = [self.embedding_func(batch) for batch in batches]
         embeddings_list = await asyncio.gather(*embedding_tasks)
 
         embeddings = np.concatenate(embeddings_list)

lightrag/kg/redis_impl.py

@@ -1,6 +1,5 @@
 import os
 from typing import Any, final
-from tqdm.asyncio import tqdm as tqdm_async
 from dataclasses import dataclass
 import pipmaster as pm
 import configparser
@@ -51,7 +50,8 @@ class RedisKVStorage(BaseKVStorage):
 
     async def upsert(self, data: dict[str, dict[str, Any]]) -> None:
         pipe = self._redis.pipeline()
-        for k, v in tqdm_async(data.items(), desc="Upserting"):
+
+        for k, v in data.items():
             pipe.set(f"{self.namespace}:{k}", json.dumps(v))
         await pipe.execute()
 

lightrag/kg/tidb_impl.py

@@ -7,7 +7,6 @@ import numpy as np
 
 from lightrag.types import KnowledgeGraph
 
-from tqdm import tqdm
 
 from ..base import BaseGraphStorage, BaseKVStorage, BaseVectorStorage
 from ..namespace import NameSpace, is_namespace
@@ -270,15 +269,8 @@ class TiDBVectorDBStorage(BaseVectorStorage):
             for i in range(0, len(contents), self._max_batch_size)
         ]
         embedding_tasks = [self.embedding_func(batch) for batch in batches]
-        embeddings_list = []
-        for f in tqdm(
-            asyncio.as_completed(embedding_tasks),
-            total=len(embedding_tasks),
-            desc="Generating embeddings",
-            unit="batch",
-        ):
-            embeddings = await f
-            embeddings_list.append(embeddings)
+        embeddings_list = await asyncio.gather(*embedding_tasks)
+
         embeddings = np.concatenate(embeddings_list)
         for i, d in enumerate(list_data):
             d["content_vector"] = embeddings[i]