langfuse-haystack 0.3.0__tar.gz → 0.5.0__tar.gz

langfuse_haystack-0.5.0/CHANGELOG.md

@@ -0,0 +1,43 @@
+# Changelog
+
+## [integrations/langfuse-v0.4.0] - 2024-09-17
+
+### 🚀 Features
+
+- Langfuse - support generation span for more LLMs (#1087)
+
+### 🚜 Refactor
+
+- Remove usage of deprecated `ChatMessage.to_openai_format` (#1001)
+
+### 📚 Documentation
+
+- Add link to langfuse in LangfuseConnector (#981)
+
+### 🧪 Testing
+
+- Do not retry tests in `hatch run test` command (#954)
+
+### ⚙️ Miscellaneous Tasks
+
+- Retry tests to reduce flakyness (#836)
+- `Langfuse` - replace DynamicChatPromptBuilder with ChatPromptBuilder (#925)
+- Remove all `DynamicChatPromptBuilder` references in Langfuse integration (#931)
+
+## [integrations/langfuse-v0.2.0] - 2024-06-18
+
+## [integrations/langfuse-v0.1.0] - 2024-06-13
+
+### 🚀 Features
+
+- Langfuse integration (#686)
+
+### 🐛 Bug Fixes
+
+- Performance optimizations and value error when streaming in langfuse (#798)
+
+### ⚙️ Miscellaneous Tasks
+
+- Use ChatMessage to_openai_format, update unit tests, pydocs (#725)
+
+<!-- generated by git-cliff -->

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: langfuse-haystack
-Version: 0.3.0
+Version: 0.5.0
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/langfuse#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/langfuse

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/example/basic_rag.py

@@ -10,6 +10,7 @@ from haystack.components.embedders import SentenceTransformersDocumentEmbedder,
 from haystack.components.generators import OpenAIGenerator
 from haystack.components.retrievers import InMemoryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.connectors.langfuse import LangfuseConnector
 
 

langfuse_haystack-0.5.0/example/chat.py

@@ -0,0 +1,64 @@
+import os
+
+# See README.md for more information on how to set up the environment variables
+# before running this script
+
+# In addition to setting the environment variables, you need to install the following packages:
+# pip install cohere-haystack anthropic-haystack
+os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
+
+from haystack import Pipeline
+from haystack.components.builders import ChatPromptBuilder
+from haystack.components.generators.chat import HuggingFaceAPIChatGenerator, OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+from haystack.utils.auth import Secret
+from haystack.utils.hf import HFGenerationAPIType
+
+from haystack_integrations.components.connectors.langfuse import LangfuseConnector
+from haystack_integrations.components.generators.anthropic import AnthropicChatGenerator
+from haystack_integrations.components.generators.cohere import CohereChatGenerator
+
+os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
+
+selected_chat_generator = "openai"
+
+generators = {
+    "openai": OpenAIChatGenerator,
+    "anthropic": AnthropicChatGenerator,
+    "hf_api": lambda: HuggingFaceAPIChatGenerator(
+        api_type=HFGenerationAPIType.SERVERLESS_INFERENCE_API,
+        api_params={"model": "mistralai/Mixtral-8x7B-Instruct-v0.1"},
+        token=Secret.from_token(os.environ["HF_API_KEY"]),
+    ),
+    "cohere": CohereChatGenerator,
+}
+
+selected_chat_generator = generators[selected_chat_generator]()
+
+if __name__ == "__main__":
+
+    pipe = Pipeline()
+    pipe.add_component("tracer", LangfuseConnector("Chat example"))
+    pipe.add_component("prompt_builder", ChatPromptBuilder())
+    pipe.add_component("llm", selected_chat_generator)
+
+    pipe.connect("prompt_builder.prompt", "llm.messages")
+
+    messages = [
+        ChatMessage.from_system("Always respond in German even if some input data is in other languages."),
+        ChatMessage.from_user("Tell me about {{location}}"),
+    ]
+
+    response = pipe.run(
+        data={
+            "prompt_builder": {
+                "template_variables": {"location": "Berlin"},
+                "template": messages,
+            },
+            "tracer": {
+                "invocation_context": {"some_key": "some_value"},
+            },
+        }
+    )
+    print(response["llm"]["replies"][0])
+    print(response["tracer"]["trace_url"])

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/pyproject.toml

@@ -47,6 +47,8 @@ dependencies = [
   "pytest",
   "pytest-rerunfailures",
   "haystack-pydoc-tools",
+  "anthropic-haystack",
+  "cohere-haystack"
 ]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
@@ -67,8 +69,8 @@ dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:. --exclude tests/}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
+style = ["ruff check {args:}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff check --fix {args:}", "style"]
 all = ["style", "typing"]
 
 [tool.hatch.metadata]
@@ -82,7 +84,10 @@ skip-string-normalization = true
 [tool.ruff]
 target-version = "py38"
 line-length = 120
-lint.select = [
+exclude = ["example", "tests"]
+
+[tool.ruff.lint]
+select = [
   "A",
   "ARG",
   "B",
@@ -108,8 +113,7 @@ lint.select = [
   "W",
   "YTT",
 ]
-
-lint.ignore = [
+ignore = [
   # Allow non-abstract empty methods in abstract base classes
   "B027",
   # Ignore checks for possible passwords
@@ -125,14 +129,13 @@ lint.ignore = [
   # Asserts
   "S101",
 ]
-lint.unfixable = [
+unfixable = [
   # Don't touch unused imports
   "F401",
 ]
-extend-exclude = ["tests", "example"]
 
 [tool.ruff.lint.isort]
-known-first-party = ["src"]
+known-first-party = ["haystack_integrations"]
 
 [tool.ruff.lint.flake8-tidy-imports]
 ban-relative-imports = "parents"

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/src/haystack_integrations/components/connectors/langfuse/langfuse_connector.py

@@ -1,8 +1,12 @@
-from haystack import component, tracing
+from typing import Any, Dict, Optional
+
+from haystack import component, logging, tracing
 
 from haystack_integrations.tracing.langfuse import LangfuseTracer
 from langfuse import Langfuse
 
+logger = logging.getLogger(__name__)
+
 
 @component
 class LangfuseConnector:
@@ -105,12 +109,20 @@ class LangfuseConnector:
         tracing.enable_tracing(self.tracer)
 
     @component.output_types(name=str, trace_url=str)
-    def run(self):
+    def run(self, invocation_context: Optional[Dict[str, Any]] = None):
         """
         Runs the LangfuseConnector component.
 
+        :param invocation_context: A dictionary with additional context for the invocation. This parameter
+            is useful when users want to mark this particular invocation with additional information, e.g.
+            a run id from their own execution framework, user id, etc. These key-value pairs are then visible
+            in the Langfuse traces.
         :returns: A dictionary with the following keys:
             - `name`: The name of the tracing component.
             - `trace_url`: The URL to the tracing data.
         """
+        logger.debug(
+            "Langfuse tracer invoked with the following context: '{invocation_context}'",
+            invocation_context=invocation_context,
+        )
         return {"name": self.name, "trace_url": self.tracer.get_trace_url()}

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/src/haystack_integrations/tracing/langfuse/tracer.py

@@ -10,8 +10,22 @@ from haystack.tracing import utils as tracing_utils
 import langfuse
 
 HAYSTACK_LANGFUSE_ENFORCE_FLUSH_ENV_VAR = "HAYSTACK_LANGFUSE_ENFORCE_FLUSH"
-_SUPPORTED_GENERATORS = ["AzureOpenAIGenerator", "OpenAIGenerator"]
-_SUPPORTED_CHAT_GENERATORS = ["AzureOpenAIChatGenerator", "OpenAIChatGenerator"]
+_SUPPORTED_GENERATORS = [
+    "AzureOpenAIGenerator",
+    "OpenAIGenerator",
+    "AnthropicGenerator",
+    "HuggingFaceAPIGenerator",
+    "HuggingFaceLocalGenerator",
+    "CohereGenerator",
+]
+_SUPPORTED_CHAT_GENERATORS = [
+    "AzureOpenAIChatGenerator",
+    "OpenAIChatGenerator",
+    "AnthropicChatGenerator",
+    "HuggingFaceAPIChatGenerator",
+    "HuggingFaceLocalChatGenerator",
+    "CohereChatGenerator",
+]
 _ALL_SUPPORTED_GENERATORS = _SUPPORTED_GENERATORS + _SUPPORTED_CHAT_GENERATORS
 
 

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/tests/test_langfuse_span.py

@@ -3,7 +3,9 @@ import os
 os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
 
 from unittest.mock import Mock
+
 from haystack.dataclasses import ChatMessage
+
 from haystack_integrations.tracing.langfuse.tracer import LangfuseSpan
 
 

{langfuse_haystack-0.3.0 → langfuse_haystack-0.5.0}/tests/test_tracer.py

@@ -1,5 +1,5 @@
 import os
-from unittest.mock import Mock, MagicMock, patch
+from unittest.mock import MagicMock, Mock, patch
 
 from haystack_integrations.tracing.langfuse.tracer import LangfuseTracer
 

langfuse_haystack-0.5.0/tests/test_tracing.py

@@ -0,0 +1,76 @@
+import os
+import random
+import time
+from urllib.parse import urlparse
+
+import pytest
+import requests
+from haystack import Pipeline
+from haystack.components.builders import ChatPromptBuilder
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+from requests.auth import HTTPBasicAuth
+
+from haystack_integrations.components.connectors.langfuse import LangfuseConnector
+from haystack_integrations.components.generators.anthropic import AnthropicChatGenerator
+from haystack_integrations.components.generators.cohere import CohereChatGenerator
+
+# don't remove (or move) this env var setting from here, it's needed to turn tracing on
+os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize(
+    "llm_class, env_var, expected_trace",
+    [
+        (OpenAIChatGenerator, "OPENAI_API_KEY", "OpenAI"),
+        (AnthropicChatGenerator, "ANTHROPIC_API_KEY", "Anthropic"),
+        (CohereChatGenerator, "COHERE_API_KEY", "Cohere"),
+    ],
+)
+def test_tracing_integration(llm_class, env_var, expected_trace):
+    if not all([os.environ.get("LANGFUSE_SECRET_KEY"), os.environ.get("LANGFUSE_PUBLIC_KEY"), os.environ.get(env_var)]):
+        pytest.skip(f"Missing required environment variables: LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY, or {env_var}")
+
+    pipe = Pipeline()
+    pipe.add_component("tracer", LangfuseConnector(name=f"Chat example - {expected_trace}", public=True))
+    pipe.add_component("prompt_builder", ChatPromptBuilder())
+    pipe.add_component("llm", llm_class())
+    pipe.connect("prompt_builder.prompt", "llm.messages")
+
+    messages = [
+        ChatMessage.from_system("Always respond in German even if some input data is in other languages."),
+        ChatMessage.from_user("Tell me about {{location}}"),
+    ]
+
+    response = pipe.run(
+        data={
+            "prompt_builder": {"template_variables": {"location": "Berlin"}, "template": messages},
+            "tracer": {"invocation_context": {"user_id": "user_42"}},
+        }
+    )
+    assert "Berlin" in response["llm"]["replies"][0].content
+    assert response["tracer"]["trace_url"]
+
+    # add a random delay between 1 and 3 seconds to make sure the trace is flushed
+    # and that the trace is available in Langfuse when we fetch it below
+    time.sleep(random.uniform(1, 3))
+
+    url = "https://cloud.langfuse.com/api/public/traces/"
+    trace_url = response["tracer"]["trace_url"]
+    uuid = os.path.basename(urlparse(trace_url).path)
+
+    try:
+        response = requests.get(
+            url + uuid, auth=HTTPBasicAuth(os.environ["LANGFUSE_PUBLIC_KEY"], os.environ["LANGFUSE_SECRET_KEY"])
+        )
+        assert response.status_code == 200, f"Failed to retrieve data from Langfuse API: {response.status_code}"
+
+        # check if the trace contains the expected LLM name
+        assert expected_trace in str(response.content)
+        # check if the trace contains the expected generation span
+        assert "GENERATION" in str(response.content)
+        # check if the trace contains the expected user_id
+        assert "user_42" in str(response.content)
+    except requests.exceptions.RequestException as e:
+        pytest.fail(f"Failed to retrieve data from Langfuse API: {e}")

langfuse_haystack-0.3.0/CHANGELOG.md

@@ -1,19 +0,0 @@
-# Changelog
-
-## [integrations/langfuse-v0.2.0] - 2024-06-18
-
-## [integrations/langfuse-v0.1.0] - 2024-06-13
-
-### 🚀 Features
-
-- Langfuse integration (#686)
-
-### 🐛 Bug Fixes
-
-- Performance optimizations and value error when streaming in langfuse (#798)
-
-### ⚙️ Miscellaneous Tasks
-
-- Use ChatMessage to_openai_format, update unit tests, pydocs (#725)
-
-<!-- generated by git-cliff -->

langfuse_haystack-0.3.0/example/chat.py

@@ -1,27 +0,0 @@
-import os
-
-os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
-
-from haystack import Pipeline
-from haystack.components.builders import ChatPromptBuilder
-from haystack.components.generators.chat import OpenAIChatGenerator
-from haystack.dataclasses import ChatMessage
-from haystack_integrations.components.connectors.langfuse import LangfuseConnector
-
-if __name__ == "__main__":
-
-    pipe = Pipeline()
-    pipe.add_component("tracer", LangfuseConnector("Chat example"))
-    pipe.add_component("prompt_builder", ChatPromptBuilder())
-    pipe.add_component("llm", OpenAIChatGenerator(model="gpt-3.5-turbo"))
-
-    pipe.connect("prompt_builder.prompt", "llm.messages")
-
-    messages = [
-        ChatMessage.from_system("Always respond in German even if some input data is in other languages."),
-        ChatMessage.from_user("Tell me about {{location}}"),
-    ]
-
-    response = pipe.run(data={"prompt_builder": {"template_variables": {"location": "Berlin"}, "template": messages}})
-    print(response["llm"]["replies"][0])
-    print(response["tracer"]["trace_url"])

langfuse_haystack-0.3.0/tests/test_tracing.py

@@ -1,55 +0,0 @@
-import os
-
-# don't remove (or move) this env var setting from here, it's needed to turn tracing on
-os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
-
-from urllib.parse import urlparse
-
-import pytest
-import requests
-
-from haystack import Pipeline
-from haystack.components.builders import ChatPromptBuilder
-from haystack.components.generators.chat import OpenAIChatGenerator
-from haystack.dataclasses import ChatMessage
-from requests.auth import HTTPBasicAuth
-
-from haystack_integrations.components.connectors.langfuse import LangfuseConnector
-
-
-@pytest.mark.integration
-@pytest.mark.skipif(
-    not os.environ.get("LANGFUSE_SECRET_KEY", None) and not os.environ.get("LANGFUSE_PUBLIC_KEY", None),
-    reason="Export an env var called LANGFUSE_SECRET_KEY and LANGFUSE_PUBLIC_KEY containing Langfuse credentials.",
-)
-def test_tracing_integration():
-
-    pipe = Pipeline()
-    pipe.add_component("tracer", LangfuseConnector(name="Chat example", public=True))  # public so anyone can verify run
-    pipe.add_component("prompt_builder", ChatPromptBuilder())
-    pipe.add_component("llm", OpenAIChatGenerator(model="gpt-3.5-turbo"))
-
-    pipe.connect("prompt_builder.prompt", "llm.messages")
-
-    messages = [
-        ChatMessage.from_system("Always respond in German even if some input data is in other languages."),
-        ChatMessage.from_user("Tell me about {{location}}"),
-    ]
-
-    response = pipe.run(data={"prompt_builder": {"template_variables": {"location": "Berlin"}, "template": messages}})
-    assert "Berlin" in response["llm"]["replies"][0].content
-    assert response["tracer"]["trace_url"]
-    url = "https://cloud.langfuse.com/api/public/traces/"
-    trace_url = response["tracer"]["trace_url"]
-    parsed_url = urlparse(trace_url)
-    # trace id is the last part of the path (after the last '/')
-    uuid = os.path.basename(parsed_url.path)
-    try:
-        # GET request with Basic Authentication on the Langfuse API
-        response = requests.get(
-            url + uuid, auth=HTTPBasicAuth(os.environ.get("LANGFUSE_PUBLIC_KEY"), os.environ.get("LANGFUSE_SECRET_KEY"))
-        )
-
-        assert response.status_code == 200, f"Failed to retrieve data from Langfuse API: {response.status_code}"
-    except requests.exceptions.RequestException as e:
-        assert False, f"Failed to retrieve data from Langfuse API: {e}"