remove tqdm and cleaned readme and ollama

README.md

@@ -344,16 +344,6 @@ rag = LightRAG(
     ),
 )
 ```
-#### Fully functional example
-
-There fully functional example `examples/lightrag_ollama_demo.py` that utilizes `gemma2:2b` model, runs only 4 requests in parallel and set context size to 32k.
-
-#### Using "Thinking" Models (e.g., DeepSeek)
-
-To return only the model's response, you can pass `reasoning_tag` in `llm_model_kwargs`.
-
-For example, for DeepSeek models, `reasoning_tag` should be set to `think`.
-
 #### 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`.

lightrag/api/requirements.txt

@@ -7,5 +7,4 @@ python-multipart
 tenacity
 tiktoken
 torch
-tqdm
 uvicorn

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]

lightrag/llm/ollama.py

@@ -4,7 +4,7 @@ if sys.version_info < (3, 9):
     from typing import AsyncIterator
 else:
     from collections.abc import AsyncIterator
-    
+
 import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
@@ -48,7 +48,7 @@ async def _ollama_model_if_cache(
     **kwargs,
 ) -> Union[str, AsyncIterator[str]]:
     stream = True if kwargs.get("stream") else False
-    
+
     kwargs.pop("max_tokens", None)
     # kwargs.pop("response_format", None) # allow json
     host = kwargs.pop("host", None)
@@ -129,4 +129,4 @@ async def ollama_embed(texts: list[str], embed_model, **kwargs) -> np.ndarray:
     kwargs["headers"] = headers
     ollama_client = ollama.Client(**kwargs)
     data = ollama_client.embed(model=embed_model, input=texts)
-    return data["embeddings"]
+    return data["embeddings"]

lightrag/operate.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import asyncio
 import json
 import re
-from tqdm.asyncio import tqdm as tqdm_async
 from typing import Any, AsyncIterator
 from collections import Counter, defaultdict
 from .utils import (
@@ -500,16 +499,8 @@ async def extract_entities(
         )
         return dict(maybe_nodes), dict(maybe_edges)
 
-    results = []
-    for result in tqdm_async(
-        asyncio.as_completed([_process_single_content(c) for c in ordered_chunks]),
-        total=len(ordered_chunks),
-        desc="Level 2 - Extracting entities and relationships",
-        unit="chunk",
-        position=1,
-        leave=False,
-    ):
-        results.append(await result)
+    tasks = [_process_single_content(c) for c in ordered_chunks]
+    results = await asyncio.gather(*tasks)
 
     maybe_nodes = defaultdict(list)
     maybe_edges = defaultdict(list)
@@ -518,41 +509,20 @@ async def extract_entities(
             maybe_nodes[k].extend(v)
         for k, v in m_edges.items():
             maybe_edges[tuple(sorted(k))].extend(v)
-    logger.debug("Inserting entities into storage...")
-    all_entities_data = []
-    for result in tqdm_async(
-        asyncio.as_completed(
-            [
-                _merge_nodes_then_upsert(k, v, knowledge_graph_inst, global_config)
-                for k, v in maybe_nodes.items()
-            ]
-        ),
-        total=len(maybe_nodes),
-        desc="Level 3 - Inserting entities",
-        unit="entity",
-        position=2,
-        leave=False,
-    ):
-        all_entities_data.append(await result)
 
-    logger.debug("Inserting relationships into storage...")
-    all_relationships_data = []
-    for result in tqdm_async(
-        asyncio.as_completed(
-            [
-                _merge_edges_then_upsert(
-                    k[0], k[1], v, knowledge_graph_inst, global_config
-                )
-                for k, v in maybe_edges.items()
-            ]
-        ),
-        total=len(maybe_edges),
-        desc="Level 3 - Inserting relationships",
-        unit="relationship",
-        position=3,
-        leave=False,
-    ):
-        all_relationships_data.append(await result)
+    all_entities_data = await asyncio.gather(
+        *[
+            _merge_nodes_then_upsert(k, v, knowledge_graph_inst, global_config)
+            for k, v in maybe_nodes.items()
+        ]
+    )
+
+    all_relationships_data = await asyncio.gather(
+        *[
+            _merge_edges_then_upsert(k[0], k[1], v, knowledge_graph_inst, global_config)
+            for k, v in maybe_edges.items()
+        ]
+    )
 
     if not len(all_entities_data) and not len(all_relationships_data):
         logger.warning(

lightrag/utils.py

@@ -19,7 +19,6 @@ import tiktoken
 from lightrag.prompt import PROMPTS
 
 
-
 VERBOSE_DEBUG = os.getenv("VERBOSE", "false").lower() == "true"
 
 
@@ -84,7 +83,6 @@ class EmbeddingFunc:
         return await self.func(*args, **kwargs)
 
 
-
 def locate_json_string_body_from_string(content: str) -> str | None:
     """Locate the JSON string body from a string"""
     try:
@@ -715,4 +713,3 @@ def get_conversation_turns(
         )
 
     return "\n".join(formatted_turns)
-

reproduce/Step_3.py

@@ -2,7 +2,6 @@ import re
 import json
 import asyncio
 from lightrag import LightRAG, QueryParam
-from tqdm import tqdm
 
 
 def extract_queries(file_path):
@@ -44,7 +43,7 @@ def run_queries_and_save_to_json(
         result_file.write("[\n")
         first_entry = True
 
-        for query_text in tqdm(queries, desc="Processing queries", unit="query"):
+        for query_text in queries:
             result, error = loop.run_until_complete(
                 process_query(query_text, rag_instance, query_param)
             )

reproduce/Step_3_openai_compatible.py

@@ -3,7 +3,6 @@ import re
 import json
 import asyncio
 from lightrag import LightRAG, QueryParam
-from tqdm import tqdm
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
@@ -76,7 +75,7 @@ def run_queries_and_save_to_json(
         result_file.write("[\n")
         first_entry = True
 
-        for query_text in tqdm(queries, desc="Processing queries", unit="query"):
+        for query_text in queries:
             result, error = loop.run_until_complete(
                 process_query(query_text, rag_instance, query_param)
             )

requirements.txt

@@ -22,7 +22,6 @@ tenacity
 
 # LLM packages
 tiktoken
-tqdm
 xxhash
 
 # Extra libraries are installed when needed using pipmaster