Remove packages for pydantic compatibility (#9217)

# Poetry updates

This PR updates LangChains poetry file to remove
any dependencies that aren't pydantic v2 compatible yet.

All packages remain usable under pydantic v1, and can be installed
separately. 

## Bumping the following packages:

* langsmith

## Removing the following packages

not used in extended unit-tests:

* zep-python, anthropic, jina, spacy, steamship, betabageldb

not used at all:

* octoai-sdk

Cleaning up extras w/ for removed packages.

## Snapshots updated

Some snapshots had to be updated due to a change in the data model in
langsmith. RunType used to be Union of Enum and string and was changed
to be string only.

libs/langchain/pyproject.toml

@@ -26,7 +26,6 @@ elasticsearch = {version = "^8", optional = true}
 opensearch-py = {version = "^2.0.0", optional = true}
 redis = {version = "^4", optional = true}
 manifest-ml = {version = "^0.0.1", optional = true}
-spacy = {version = "^3", optional = true}
 nltk = {version = "^3", optional = true}
 transformers = {version = "^4", optional = true}
 beautifulsoup4 = {version = "^4", optional = true}
@@ -42,7 +41,6 @@ marqo = {version = "^0.11.0", optional=true}
 google-api-python-client = {version = "2.70.0", optional = true}
 google-auth = {version = "^2.18.1", optional = true}
 wolframalpha = {version = "5.0.0", optional = true}
-anthropic = {version = "^0.3", optional = true}
 qdrant-client = {version = "^1.3.1", optional = true, python = ">=3.8.1,<3.12"}
 dataclasses-json = "^0.5.7"
 tensorflow-text = {version = "^2.11.0", optional = true, python = "^3.10, <3.12"}
@@ -52,8 +50,6 @@ openai = {version = "^0", optional = true}
 nlpcloud = {version = "^1", optional = true}
 nomic = {version = "^1.0.43", optional = true}
 huggingface_hub = {version = "^0", optional = true}
-octoai-sdk = {version = "^0.1.1", optional = true}
-jina = {version = "^3.14", optional = true}
 google-search-results = {version = "^2", optional = true}
 sentence-transformers = {version = "^2", optional = true}
 aiohttp = "^3.8.3"
@@ -81,7 +77,6 @@ pexpect = {version = "^4.8.0", optional = true}
 pyvespa = {version = "^0.33.0", optional = true}
 O365 = {version = "^2.0.26", optional = true}
 jq = {version = "^1.4.1", optional = true}
-steamship = {version = "^2.16.9", optional = true}
 pdfminer-six = {version = "^20221105", optional = true}
 docarray = {version="^0.32.0", extras=["hnswlib"], optional=true}
 lxml = {version = "^4.9.2", optional = true}
@@ -91,7 +86,6 @@ gql = {version = "^3.4.1", optional = true}
 pandas = {version = "^2.0.1", optional = true}
 telethon = {version = "^1.28.5", optional = true}
 neo4j = {version = "^5.8.1", optional = true}
-zep-python = {version = ">=1.0.1,<1.1.0", optional = true}
 langkit = {version = ">=0.0.6, <0.1.0", optional = true}
 chardet = {version="^5.1.0", optional=true}
 requests-toolbelt = {version = "^1.0.0", optional = true}
@@ -120,11 +114,10 @@ cassio = {version = "^0.0.7", optional = true}
 rdflib = {version = "^6.3.2", optional = true}
 sympy = {version = "^1.12", optional = true}
 rapidfuzz = {version = "^3.1.1", optional = true}
-langsmith = "~0.0.11"
+langsmith = "~0.0.21"
 rank-bm25 = {version = "^0.2.2", optional = true}
 amadeus = {version = ">=8.1.0", optional = true}
 geopandas = {version = "^0.13.1", optional = true}
-xinference = {version = "^0.0.6", optional = true}
 python-arango = {version = "^7.5.9", optional = true}
 gitpython = {version = "^3.1.32", optional = true}
 librosa = {version="^0.10.0.post2", optional = true }
@@ -133,7 +126,6 @@ newspaper3k = {version = "^0.2.8", optional = true}
 amazon-textract-caller = {version = "<2", optional = true}
 xata = {version = "^1.0.0a7", optional = true}
 xmltodict = {version = "^0.13.0", optional = true}
-betabageldb = {version = "0.2.32", optional = true, python = ">=3.7,<3.11"}
 
 
 [tool.poetry.group.test.dependencies]
@@ -205,7 +197,7 @@ playwright = "^1.28.0"
 setuptools = "^67.6.1"
 
 [tool.poetry.extras]
-llms = ["anthropic", "clarifai", "cohere", "openai", "openllm", "openlm", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers", "xinference"]
+llms = ["clarifai", "cohere", "openai", "openllm", "openlm", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers", ]
 qdrant = ["qdrant-client"]
 openai = ["openai", "tiktoken"]
 text_helpers = ["chardet"]
@@ -225,13 +217,11 @@ azure = [
     "azure-search-documents",
 ]
 all = [
-    "anthropic",
     "clarifai",
     "cohere",
     "openai",
     "nlpcloud",
     "huggingface_hub",
-    "jina",
     "manifest-ml",
     "elasticsearch",
     "opensearch-py",
@@ -239,7 +229,6 @@ all = [
     "faiss-cpu",
     "sentence-transformers",
     "transformers",
-    "spacy",
     "nltk",
     "wikipedia",
     "beautifulsoup4",
@@ -283,7 +272,6 @@ all = [
     "O365",
     "jq",
     "docarray",
-    "steamship",
     "pdfminer-six",
     "lxml",
     "requests-toolbelt",
@@ -298,10 +286,8 @@ all = [
     "nebula3-python",
     "awadb",
     "esprima",
-    "octoai-sdk",
     "rdflib",
     "amadeus",
-    "xinference",
     "librosa",
     "python-arango",
 ]
@@ -330,7 +316,6 @@ extended_testing = [
  "pandas",
  "telethon",
  "psychicapi",
- "zep-python",
  "gql",
  "requests_toolbelt",
  "html2text",
@@ -345,14 +330,11 @@ extended_testing = [
  "rank_bm25",
  "geopandas",
  "jinja2",
- "xinference",
  "gitpython",
  "newspaper3k",
  "feedparser",
  "xata",
  "xmltodict",
- "betabageldb",
- "anthropic",
 ]
 
 [tool.ruff]

libs/langchain/tests/integration_tests/chat_models/test_anthropic.py

@@ -95,3 +95,19 @@ def test_formatting() -> None:
     chat_messages = [HumanMessage(content="Hello"), AIMessage(content="Answer:")]
     result = chat._convert_messages_to_prompt(chat_messages)
     assert result == "\n\nHuman: Hello\n\nAssistant: Answer:"
+
+
+def test_anthropic_model_kwargs() -> None:
+    llm = ChatAnthropic(model_kwargs={"foo": "bar"})
+    assert llm.model_kwargs == {"foo": "bar"}
+
+
+def test_anthropic_invalid_model_kwargs() -> None:
+    with pytest.raises(ValueError):
+        ChatAnthropic(model_kwargs={"max_tokens_to_sample": 5})
+
+
+def test_anthropic_incorrect_field() -> None:
+    with pytest.warns(match="not default parameter"):
+        llm = ChatAnthropic(foo="bar")
+    assert llm.model_kwargs == {"foo": "bar"}

libs/langchain/tests/unit_tests/schema/test_runnable.py

@@ -1,4 +1,3 @@
-import warnings
 from typing import Any, Dict, List, Optional
 from uuid import UUID
 
@@ -35,7 +34,6 @@ from langchain.schema.runnable import (
     RunnableSequence,
     RunnableWithFallbacks,
 )
-from langchain.utils.pydantic import PYDANTIC_MAJOR_VERSION
 
 
 class FakeTracer(BaseTracer):
@@ -253,13 +251,7 @@ async def test_prompt_with_chat_model(
         ]
     )
 
-    if PYDANTIC_MAJOR_VERSION == 1:
     assert tracer.runs == snapshot
-    else:
-        warnings.warn(
-            f"testing snapshot for pydantic version {PYDANTIC_MAJOR_VERSION} is "
-            f"not supported yet"
-        )
 
     mocker.stop(prompt_spy)
     mocker.stop(chat_spy)
@@ -361,13 +353,7 @@ async def test_prompt_with_llm(
             HumanMessage(content="What is your name?"),
         ]
     )
-    if PYDANTIC_MAJOR_VERSION == 1:
     assert tracer.runs == snapshot
-    else:
-        warnings.warn(
-            f"testing snapshot for pydantic version {PYDANTIC_MAJOR_VERSION} is "
-            f"not supported yet"
-        )
     mocker.stop(prompt_spy)
     mocker.stop(llm_spy)
 
@@ -400,13 +386,7 @@ async def test_prompt_with_llm(
             ]
         ),
     ]
-    if PYDANTIC_MAJOR_VERSION == 1:
     assert tracer.runs == snapshot
-    else:
-        warnings.warn(
-            f"testing snapshot for pydantic version {PYDANTIC_MAJOR_VERSION} is "
-            f"not supported yet"
-        )
     mocker.stop(prompt_spy)
     mocker.stop(llm_spy)
 
@@ -465,13 +445,7 @@ def test_prompt_with_chat_model_and_parser(
     )
     assert parser_spy.call_args.args[1] == AIMessage(content="foo, bar")
 
-    if PYDANTIC_MAJOR_VERSION == 1:
     assert tracer.runs == snapshot
-    else:
-        warnings.warn(
-            f"testing snapshot for pydantic version {PYDANTIC_MAJOR_VERSION} is "
-            f"not supported yet"
-        )
 
 
 @freeze_time("2023-01-01")
@@ -529,13 +503,8 @@ def test_combining_sequences(
     assert combined_chain.invoke(
         {"question": "What is your name?"}, dict(callbacks=[tracer])
     ) == ["baz", "qux"]
-    if PYDANTIC_MAJOR_VERSION == 1:
+
     assert tracer.runs == snapshot
-    else:
-        warnings.warn(
-            f"testing snapshot for pydantic version {PYDANTIC_MAJOR_VERSION} is "
-            f"not supported yet"
-        )
 
 
 @freeze_time("2023-01-01")