Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

Fix a Pretty print and httpx bugs (#419)

Louis Choquel9d8eabf35a80
diff --git a/docs/pages/build-reliable-ai-workflows-with-pipelex/pipe-operators/PipeLLM.md b/docs/pages/build-reliable-ai-workflows-with-pipelex/pipe-operators/PipeLLM.md
index 5cc4ab036..b0a173695 100644
--- a/docs/pages/build-reliable-ai-workflows-with-pipelex/pipe-operators/PipeLLM.md
+++ b/docs/pages/build-reliable-ai-workflows-with-pipelex/pipe-operators/PipeLLM.md
@@ -28,7 +28,7 @@ description = "Describe an image"
inputs = { image = "Image" }
output = "VisualDescription"
prompt = """
-Describe the provided image in great detail.
+Describe the provided image in great detail: $image
"""
```
@@ -46,7 +46,7 @@ description = "Analyze wedding photo"
inputs = { wedding_photo = "Photo" }
output = "PhotoAnalysis"
prompt = """
-Analyze this wedding photo and describe the key moments captured.
+Analyze this wedding photo and describe the key moments captured: $wedding_photo
"""
```
@@ -61,7 +61,7 @@ description = "Analyze the visual layout of a page"
inputs = { "page_content.page_view" = "Image" }
output = "LayoutAnalysis"
prompt = """
-Analyze the visual layout and design elements of this page.
+Analyze the visual layout and design elements of this page: $page_content.page_view
Focus on typography, spacing, and overall composition.
"""
```
@@ -86,7 +86,7 @@ inputs = {
}
output = "ImageComparison"
prompt = """
-Compare these two images and describe their similarities and differences.
+Compare these two images and describe their similarities and differences: $first_image and $second_image
"""
```
@@ -106,7 +106,7 @@ output = "DocumentAnalysis"
prompt = """
Given this context: $context
-Analyze the document page shown in the image and explain how it relates to the provided context.
+Analyze the document page shown in the image and explain how it relates to the provided context: $document.page_view
"""
```
@@ -125,7 +125,7 @@ Analyze the document page shown in the image and explain how it relates to the p
| `model` | string or table | Specifies the LLM choice by name, setting, or preset to use. | No |
| `model_to_structure` | string or table | Specifies the LLM choice by name, setting, or preset to use for structuring after preliminary text generation. | No |
| `system_prompt` | string | A system-level prompt to guide the LLM's behavior (e.g., "You are a helpful assistant"). Can be inline text or a reference to a template file (`"file:path/to/prompt.md"`). | No |
-| `prompt_template` | string | A template for the user prompt. Use `$` for inline variables (e.g., `$topic`) and `@` to insert the content of an entire input (e.g., `@text_to_summarize`). **Note**: Do not use `@` or `$` for image variables. | No |
+| `prompt` | string | A template for the user prompt. Use `$` for inline variables (e.g., `$topic`) and `@` to insert the content of an entire input (e.g., `@text_to_summarize`). Image variables should also be tagged with `$` or `@`. | No |
| `structuring_method` | string | The method for generating structured output. Can be `direct` or `preliminary_text`. Defaults to the global configuration. | No |
### Output Multiplicity
@@ -171,7 +171,7 @@ Write a four-line poem about pipes.
### Text-to-Text Example
-This pipe summarizes an input text, using a `prompt_template` to inject the input.
+This pipe summarizes an input text, using a `prompt` to inject the input.
```plx
[pipe.summarize_text]
@@ -199,7 +199,7 @@ description = "Extract table data from an image"
inputs = { image = "TableScreenshot" }
output = "TableData"
prompt = """
-Extract the table data from this image and format it as a structured table.
+Extract the table data from this image and format it as a structured table: $image
"""
```
diff --git a/docs/pages/cookbook-examples/extract-proof-of-purchase.md b/docs/pages/cookbook-examples/extract-proof-of-purchase.md
index e79a230c8..aa458a2c9 100644
--- a/docs/pages/cookbook-examples/extract-proof-of-purchase.md
+++ b/docs/pages/cookbook-examples/extract-proof-of-purchase.md
@@ -61,7 +61,7 @@ model = "llm_for_img_to_text"
structuring_method = "preliminary_text"
system_prompt = """You are a multimodal LLM, expert at converting images into perfect markdown."""
prompt = """
-You are given an image of a proof of purchase.
+You are given an image of a proof of purchase: $page_content.page_view
Your role is to convert the image into perfect markdown.
To help you do so, you are given the text extracted from the page by an OCR model.
diff --git a/docs/pages/cookbook-examples/extract-table.md b/docs/pages/cookbook-examples/extract-table.md
index a7f68ebf5..182acf30e 100644
--- a/docs/pages/cookbook-examples/extract-table.md
+++ b/docs/pages/cookbook-examples/extract-table.md
@@ -78,7 +78,7 @@ description = "Review an HTML table"
inputs = { table_screenshot = "TableScreenshot", html_table = "HtmlTable" }
output = "HtmlTable"
prompt = """
-Your role is to correct an html_table to make sure that it matches the one in the provided image.
+Your role is to correct an html_table to make sure that it matches the one in the provided image: $table_screenshot
@html_table
diff --git a/docs/pages/cookbook-examples/invoice-extractor.md b/docs/pages/cookbook-examples/invoice-extractor.md
index 38653df1a..233e2c687 100644
--- a/docs/pages/cookbook-examples/invoice-extractor.md
+++ b/docs/pages/cookbook-examples/invoice-extractor.md
@@ -82,7 +82,7 @@ inputs = { "invoice_page.page_view" = "Image", invoice_details = "InvoiceDetails
output = "Invoice"
model = "llm_to_extract_invoice"
prompt = """
-Extract invoice information from this invoice:
+Extract invoice information from this invoice: $invoice_page.page_view
The category of this invoice is: $invoice_details.category.
diff --git a/pipelex/cogt/model_backends/backend_library.py b/pipelex/cogt/model_backends/backend_library.py
index 3f1dc15e8..9e956e421 100644
--- a/pipelex/cogt/model_backends/backend_library.py
+++ b/pipelex/cogt/model_backends/backend_library.py
@@ -97,8 +97,9 @@ class InferenceBackendLibrary(RootModel[InferenceBackendLibraryRoot]):
) from var_fallback_pattern_exc
except VarNotFoundError as var_not_found_exc:
msg = (
- f"Variable substitution failed due to a 'variable not found' error in file '{backends_library_path}':"
- f"\n{var_not_found_exc}\nRun mode: '{runtime_manager.run_mode}'"
+ f"Variable substitution failed due to a 'variable not found' error in file '{backends_library_path}':\n"
+ f"Backend name: '{backend_name}', Variable name: '{var_not_found_exc.var_name}'\n"
+ f"{var_not_found_exc}\nRun mode: '{runtime_manager.run_mode}'"
)
raise InferenceBackendCredentialsError(
error_type=InferenceBackendCredentialsErrorType.VAR_NOT_FOUND,
diff --git a/pipelex/core/stuffs/stuff_content.py b/pipelex/core/stuffs/stuff_content.py
index c281e2131..962532aa1 100644
--- a/pipelex/core/stuffs/stuff_content.py
+++ b/pipelex/core/stuffs/stuff_content.py
@@ -1,11 +1,11 @@
from abc import ABC
-from typing import Any, TypeVar, cast
+from typing import Any, TypeVar
from kajson import kajson
from typing_extensions import override
from pipelex.cogt.templating.templating_style import TextFormat
-from pipelex.tools.misc.json_utils import remove_none_values_from_dict
+from pipelex.tools.misc.json_utils import remove_none_values
from pipelex.tools.misc.pretty import pretty_print
from pipelex.tools.typing.pydantic_utils import CustomBaseModel
@@ -55,6 +55,5 @@ class StuffContent(ABC, CustomBaseModel):
return kajson.dumps(self.smart_dump(), indent=4)
def pretty_print_content(self, title: str | None = None, number: int | None = None) -> None: # noqa: ARG002
- the_dict: dict[str, Any] = cast("dict[str, Any]", self.smart_dump())
- the_dict = remove_none_values_from_dict(data=the_dict)
- pretty_print(the_dict, title=title)
+ json_content = remove_none_values(json_content=self.smart_dump())
+ pretty_print(json_content, title=title)
diff --git a/pipelex/plugins/openai/openai_factory.py b/pipelex/plugins/openai/openai_factory.py
index fccc3265f..6543ae78e 100644
--- a/pipelex/plugins/openai/openai_factory.py
+++ b/pipelex/plugins/openai/openai_factory.py
@@ -48,6 +48,12 @@ class OpenAIFactory:
msg = f"Plugin '{plugin}' is not supported by OpenAIFactory"
raise OpenAIFactoryError(msg) from exc
+ # We have a workaround here:
+ # OpenAI can be used without any API key (for instance when pointing to local Ollama) but the SDK,
+ # as it is, raises if there is not API key (api_key is None and there is not env var).
+ # But it works fine with an empty string.
+ api_key = backend.api_key or ""
+
the_client: openai.AsyncOpenAI
match sdk_variant:
case OpenAISdkVariant.AZURE_OPENAI:
@@ -57,20 +63,19 @@ class OpenAIFactory:
raise OpenAIFactoryError(msg)
the_client = openai.AsyncAzureOpenAI(
azure_endpoint=backend.endpoint,
- api_key=backend.api_key,
+ api_key=api_key,
api_version=backend.get_extra_config(AzureExtraField.API_VERSION),
)
-
case OpenAISdkVariant.OPENAI:
log.verbose(f"Making AsyncOpenAI client with endpoint: {backend.endpoint}")
the_client = openai.AsyncOpenAI(
- api_key=backend.api_key,
+ api_key=api_key,
base_url=backend.endpoint,
)
case OpenAISdkVariant.OPENAI_ALT_IMG_GEN:
log.verbose(f"Making AsyncOpenAI client with endpoint: {backend.endpoint}")
the_client = openai.AsyncOpenAI(
- api_key=backend.api_key,
+ api_key=api_key,
base_url=backend.endpoint,
)
diff --git a/pipelex/tools/misc/file_fetch_utils.py b/pipelex/tools/misc/file_fetch_utils.py
index cb295dbe2..8612ef0a9 100644
--- a/pipelex/tools/misc/file_fetch_utils.py
+++ b/pipelex/tools/misc/file_fetch_utils.py
@@ -1,12 +1,15 @@
import httpx
from httpx import Response
+from pipelex.tools.misc.http_utils import get_user_agent
+
async def fetch_file_from_url_httpx_async(
url: str,
request_timeout: int | None = None,
) -> bytes:
- async with httpx.AsyncClient() as client:
+ user_agent = get_user_agent()
+ async with httpx.AsyncClient(headers={"User-Agent": user_agent}) as client:
response: Response = await client.get(
url,
timeout=request_timeout,
@@ -21,7 +24,8 @@ def fetch_file_from_url_httpx(
url: str,
request_timeout: int | None = None,
) -> bytes:
- with httpx.Client() as client:
+ user_agent = get_user_agent()
+ with httpx.Client(headers={"User-Agent": user_agent}) as client:
response: Response = client.get(
url,
timeout=request_timeout,
diff --git a/pipelex/tools/misc/http_utils.py b/pipelex/tools/misc/http_utils.py
new file mode 100644
index 000000000..7c994eb61
--- /dev/null
+++ b/pipelex/tools/misc/http_utils.py
@@ -0,0 +1,8 @@
+from pipelex.tools.misc.package_utils import get_package_version
+from pipelex.urls import URLs
+
+
+def get_user_agent() -> str:
+ version = get_package_version()
+ homepage_url = URLs.homepage
+ return f"Pipelex/{version} ({homepage_url})"
diff --git a/pipelex/urls.py b/pipelex/urls.py
index adec05ebf..7d90529a1 100644
--- a/pipelex/urls.py
+++ b/pipelex/urls.py
@@ -1,3 +1,7 @@
class URLs:
+ homepage = "https://pipelex.com"
+ repository = "https://github.com/Pipelex/pipelex"
+ documentation = "https://docs.pipelex.com/"
+ changelog = "https://docs.pipelex.com/changelog/"
discord = "https://go.pipelex.com/discord"
pipe_func_docs = "https://docs.pipelex.com/pages/build-reliable-ai-workflows-with-pipelex/pipe-operators/PipeFunc"