langroid 0.1.198__tar.gz → 0.1.200__tar.gz

{langroid-0.1.198 → langroid-0.1.200}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.198
+Version: 0.1.200
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -11,9 +11,11 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Provides-Extra: chainlit
+Provides-Extra: chromadb
 Provides-Extra: hf-embeddings
 Provides-Extra: litellm
 Provides-Extra: metaphor
+Provides-Extra: mkdocs
 Provides-Extra: mysql
 Provides-Extra: neo4j
 Provides-Extra: postgres
@@ -27,7 +29,7 @@ Requires-Dist: autopep8 (>=2.0.2,<3.0.0)
 Requires-Dist: black[jupyter] (>=23.3.0,<24.0.0)
 Requires-Dist: bs4 (>=0.0.1,<0.0.2)
 Requires-Dist: chainlit (>=1.0.301,<2.0.0) ; extra == "chainlit"
-Requires-Dist: chromadb (>=0.4.21,<=0.4.23)
+Requires-Dist: chromadb (>=0.4.21,<=0.4.23) ; extra == "chromadb"
 Requires-Dist: colorlog (>=6.7.0,<7.0.0)
 Requires-Dist: docstring-parser (>=0.15,<0.16)
 Requires-Dist: duckduckgo-search (>=4.4,<5.0)
@@ -37,6 +39,7 @@ Requires-Dist: fire (>=0.5.0,<0.6.0)
 Requires-Dist: flake8 (>=6.0.0,<7.0.0)
 Requires-Dist: google-api-python-client (>=2.95.0,<3.0.0)
 Requires-Dist: halo (>=0.0.31,<0.0.32)
+Requires-Dist: huggingface-hub (>=0.21.2,<0.22.0) ; extra == "transformers"
 Requires-Dist: jinja2 (>=3.1.2,<4.0.0)
 Requires-Dist: lancedb (>=0.4.1,<0.5.0)
 Requires-Dist: litellm (>=1.23.0,<2.0.0) ; extra == "litellm"
@@ -44,15 +47,15 @@ Requires-Dist: lxml (>=4.9.3,<5.0.0)
 Requires-Dist: meilisearch (>=0.28.3,<0.29.0)
 Requires-Dist: meilisearch-python-sdk (>=2.2.3,<3.0.0)
 Requires-Dist: metaphor-python (>=0.1.23,<0.2.0) ; extra == "metaphor"
-Requires-Dist: mkdocs (>=1.4.2,<2.0.0)
-Requires-Dist: mkdocs-awesome-pages-plugin (>=2.8.0,<3.0.0)
-Requires-Dist: mkdocs-gen-files (>=0.4.0,<0.5.0)
-Requires-Dist: mkdocs-jupyter (>=0.24.1,<0.25.0)
-Requires-Dist: mkdocs-literate-nav (>=0.6.0,<0.7.0)
-Requires-Dist: mkdocs-material (>=9.1.5,<10.0.0)
+Requires-Dist: mkdocs (>=1.4.2,<2.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-awesome-pages-plugin (>=2.8.0,<3.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-gen-files (>=0.4.0,<0.5.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-jupyter (>=0.24.1,<0.25.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-literate-nav (>=0.6.0,<0.7.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-material (>=9.1.5,<10.0.0) ; extra == "mkdocs"
 Requires-Dist: mkdocs-rss-plugin (>=1.8.0,<2.0.0)
-Requires-Dist: mkdocs-section-index (>=0.3.5,<0.4.0)
-Requires-Dist: mkdocstrings[python] (>=0.21.2,<0.22.0)
+Requires-Dist: mkdocs-section-index (>=0.3.5,<0.4.0) ; extra == "mkdocs"
+Requires-Dist: mkdocstrings[python] (>=0.21.2,<0.22.0) ; extra == "mkdocs"
 Requires-Dist: momento (>=1.10.2,<2.0.0)
 Requires-Dist: mypy (>=1.7.0,<2.0.0)
 Requires-Dist: neo4j (>=5.14.1,<6.0.0) ; extra == "neo4j"

{langroid-0.1.198 → langroid-0.1.200}/langroid/agent/special/doc_chat_agent.py

@@ -68,6 +68,14 @@ DEFAULT_DOC_CHAT_SYSTEM_MESSAGE = """
 You are a helpful assistant, helping me understand a collection of documents.
 """
 
+has_sentence_transformers = False
+try:
+    from sentence_transformer import SentenceTransformer  # noqa: F401
+
+    has_sentence_transformers = True
+except ImportError:
+    pass
+
 
 class DocChatAgentConfig(ChatAgentConfig):
     system_message: str = DEFAULT_DOC_CHAT_SYSTEM_MESSAGE
@@ -98,7 +106,9 @@ class DocChatAgentConfig(ChatAgentConfig):
     n_fuzzy_neighbor_words: int = 100  # num neighbor words to retrieve for fuzzy match
     use_fuzzy_match: bool = True
     use_bm25_search: bool = True
-    cross_encoder_reranking_model: str = "cross-encoder/ms-marco-MiniLM-L-6-v2"
+    cross_encoder_reranking_model: str = (
+        "cross-encoder/ms-marco-MiniLM-L-6-v2" if has_sentence_transformers else ""
+    )
     rerank_diversity: bool = True  # rerank to maximize diversity?
     rerank_periphery: bool = True  # rerank to avoid Lost In the Middle effect?
     embed_batch_size: int = 500  # get embedding of at most this many at a time
@@ -156,7 +166,7 @@ class DocChatAgentConfig(ChatAgentConfig):
         collection_name="doc-chat-lancedb",
         replace_collection=True,
         storage_path=".lancedb/data/",
-        embedding=oai_embed_config,
+        embedding=hf_embed_config if has_sentence_transformers else oai_embed_config,
     )
     llm: OpenAIGPTConfig = OpenAIGPTConfig(
         type="openai",

{langroid-0.1.198 → langroid-0.1.200}/langroid/language_models/prompt_formatter/hf_formatter.py

@@ -6,9 +6,8 @@ models will have the same tokenizer, so we just use the first one.
 """
 import logging
 import re
-from typing import Any, List, Set, Type
+from typing import Any, List, Set, Tuple, Type
 
-from huggingface_hub import HfApi, ModelFilter
 from jinja2.exceptions import TemplateError
 
 from langroid.language_models.base import LanguageModel, LLMMessage, Role
@@ -18,7 +17,7 @@ from langroid.language_models.prompt_formatter.base import PromptFormatter
 logger = logging.getLogger(__name__)
 
 
-def try_import_AutoTokenizer() -> Type[Any]:
+def try_import_hf_modules() -> Tuple[Type[Any], Type[Any], Type[Any]]:
     """
     Attempts to import the AutoTokenizer class from the transformers package.
     Returns:
@@ -27,14 +26,18 @@ def try_import_AutoTokenizer() -> Type[Any]:
         ImportError: If the transformers package is not installed.
     """
     try:
+        from huggingface_hub import HfApi, ModelFilter
         from transformers import AutoTokenizer
 
-        return AutoTokenizer  # type: ignore
+        return AutoTokenizer, HfApi, ModelFilter
     except ImportError:
         raise ImportError(
             """
-            You are trying to use the HuggingFace transformers.AutoTokenizer,
-            but the `transformers` package is not installed 
+            You are trying to use some/all of:
+            HuggingFace transformers.AutoTokenizer,
+            huggingface_hub.HfApi, 
+            huggingface_hub.ModelFilter,
+            but these are not not installed 
             by default with Langroid. Please install langroid using the 
             `transformers` extra, like so:
             pip install "langroid[transformers]"
@@ -44,6 +47,7 @@ def try_import_AutoTokenizer() -> Type[Any]:
 
 
 def find_hf_formatter(model_name: str) -> str:
+    AutoTokenizer, HfApi, ModelFilter = try_import_hf_modules()
     hf_api = HfApi()
     # try to find a matching model, with progressivly shorter prefixes of model_name
     model_name = model_name.lower().split("/")[-1]
@@ -61,7 +65,7 @@ def find_hf_formatter(model_name: str) -> str:
             mdl = next(models)
         except StopIteration:
             continue
-        AutoTokenizer = try_import_AutoTokenizer()
+
         tokenizer = AutoTokenizer.from_pretrained(mdl.id)
         if tokenizer.chat_template is not None:
             return str(mdl.id)
@@ -73,6 +77,7 @@ class HFFormatter(PromptFormatter):
 
     def __init__(self, config: HFPromptFormatterConfig):
         super().__init__(config)
+        AutoTokenizer, HfApi, ModelFilter = try_import_hf_modules()
         self.config: HFPromptFormatterConfig = config
         hf_api = HfApi()
         models = hf_api.list_models(
@@ -85,7 +90,7 @@ class HFFormatter(PromptFormatter):
             mdl = next(models)
         except StopIteration:
             raise ValueError(f"Model {config.model_name} not found on HuggingFace Hub")
-        AutoTokenizer = try_import_AutoTokenizer()
+
         self.tokenizer = AutoTokenizer.from_pretrained(mdl.id)
         if self.tokenizer.chat_template is None:
             raise ValueError(

{langroid-0.1.198 → langroid-0.1.200}/langroid/vector_store/__init__.py

@@ -1,22 +1,30 @@
 from . import base
-from . import chromadb
+
 from . import qdrantdb
 from . import meilisearch
 from . import lancedb
 
-from .chromadb import ChromaDBConfig, ChromaDB
 from .qdrantdb import QdrantDBConfig, QdrantDB
 from .meilisearch import MeiliSearch, MeiliSearchConfig
 from .lancedb import LanceDB, LanceDBConfig
 
+has_chromadb = False
+try:
+    from . import chromadb
+    from .chromadb import ChromaDBConfig, ChromaDB
+
+    chromadb  # silence linters
+    ChromaDB
+    ChromaDBConfig
+    has_chromadb = True
+except ImportError:
+    pass
+
 __all__ = [
     "base",
-    "chromadb",
     "qdrantdb",
     "meilisearch",
     "lancedb",
-    "ChromaDBConfig",
-    "ChromaDB",
     "QdrantDBConfig",
     "QdrantDB",
     "MeiliSearch",
@@ -24,3 +32,6 @@ __all__ = [
     "LanceDB",
     "LanceDBConfig",
 ]
+
+if has_chromadb:
+    __all__.extend(["chromadb", "ChromaDBConfig", "ChromaDB"])

{langroid-0.1.198 → langroid-0.1.200}/langroid/vector_store/chromadb.py

@@ -2,8 +2,6 @@ import json
 import logging
 from typing import Any, Dict, List, Optional, Sequence, Tuple
 
-import chromadb
-
 from langroid.embedding_models.base import (
     EmbeddingModel,
     EmbeddingModelsConfig,
@@ -28,6 +26,17 @@ class ChromaDBConfig(VectorStoreConfig):
 class ChromaDB(VectorStore):
     def __init__(self, config: ChromaDBConfig = ChromaDBConfig()):
         super().__init__(config)
+        try:
+            import chromadb
+        except ImportError:
+            raise ImportError(
+                """
+                ChromaDB is not installed by default with Langroid.
+                If you want to use it, please install it with the `chromadb` extra, e.g.
+                pip install "langroid[chromadb]"
+                or an equivalent command.
+                """
+            )
         self.config = config
         emb_model = EmbeddingModel.create(config.embedding)
         self.embedding_fn = emb_model.embedding_fn()

{langroid-0.1.198 → langroid-0.1.200}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.1.198"
+version = "0.1.200"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"
@@ -8,15 +8,15 @@ license = "MIT"
 
 [tool.poetry.dependencies]
 python = ">=3.9.1,<3.12"
-mkdocs = "^1.4.2"
-mkdocs-material = "^9.1.5"
-mkdocstrings = {extras = ["python"], version = "^0.21.2"}
-mkdocs-awesome-pages-plugin = "^2.8.0"
-mkdocs-gen-files = "^0.4.0"
-mkdocs-literate-nav = "^0.6.0"
-mkdocs-section-index = "^0.3.5"
-mkdocs-jupyter = "^0.24.1"
-chromadb = ">=0.4.21, <=0.4.23"
+mkdocs = {version="^1.4.2", optional=true}
+mkdocs-material = {version="^9.1.5", optional=true}
+mkdocstrings = {extras = ["python"], version = "^0.21.2", optional=true}
+mkdocs-awesome-pages-plugin = {version="^2.8.0", optional=true}
+mkdocs-gen-files = {version="^0.4.0", optional=true}
+mkdocs-literate-nav = {version="^0.6.0", optional=true}
+mkdocs-section-index = {version="^0.3.5", optional=true}
+mkdocs-jupyter = {version="^0.24.1", optional=true}
+chromadb = {version=">=0.4.21, <=0.4.23", optional=true}
 onnxruntime = "1.16.1"
 fire = "^0.5.0"
 black = {extras = ["jupyter"], version = "^23.3.0"}
@@ -87,12 +87,13 @@ metaphor-python = {version = "^0.1.23", optional = true}
 chainlit = {version = "^1.0.301", optional = true}
 python-socketio = {version="^5.11.0", optional=true}
 duckduckgo-search = "^4.4"
+huggingface-hub = {version="^0.21.2", optional=true}
 
 [tool.poetry.extras]
 # install these using `poetry install -E [...]` where [...] is one of the extras below
 # or install multiple extras using, e.g.,  `poetry install -E "litellm mysql"
 hf-embeddings = ["sentence-transformers", "torch"]
-transformers = ["transformers"]
+transformers = ["transformers", "huggingface-hub"]
 unstructured = ["unstructured"]
 postgres = ["psycopg2", "pytest-postgresql"]
 mysql = ["pymysql", "pytest-mysql"]
@@ -101,6 +102,9 @@ neo4j = ["neo4j"]
 sciphi = ["agent-search"]
 metaphor = ["metaphor-python"]
 chainlit = ["chainlit", "python-socketio"]
+chromadb = ["chromadb"]
+mkdocs = ["mkdocs", "mkdocs-material", "mkdocstrings", "mkdocs-awesome-pages-plugin",
+    "mkdocs-gen-files", "mkdocs-literate-nav", "mkdocs-section-index", "mkdocs-jupyter"]
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.3.1"