You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`. Use these directly or refine them when appropriate.
47
+
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`, `JSON`. Use these directly or refine them when appropriate.
46
48
47
49
**Refining Native Concepts:**
48
50
To create a concept that specializes a native concept without adding fields:
@@ -70,7 +72,7 @@ output = "ConceptName"
70
72
The pipes will all have at least this base definition.
71
73
- `inputs`: Dictionary of key being the variable used in the prompts, and the value being the ConceptName. It should ALSO LIST THE INPUTS OF THE INTERMEDIATE STEPS (if PipeSequence) or of the conditional pipes (if PipeCondition).
That means that the pipe validate_expense is missing the input `invoice` because one of the subpipe is needing it.
76
78
@@ -857,21 +859,6 @@ But don't write documentation unless asked explicitly to.
857
859
858
860
## Guide to execute a pipeline and write example code
859
861
860
-
### Prerequisites: Virtual Environment
861
-
862
-
**CRITICAL**: Before running any `pipelex` commands or `pytest`, you MUST activate the appropriate Python virtual environment. Without proper venv activation, these commands will not work.
863
-
864
-
For standard installations, the virtual environment is named `.venv`. Always check this first:
865
-
866
-
```bash
867
-
## Activate the virtual environment (standard installation)
868
-
source .venv/bin/activate # On macOS/Linux
869
-
## or
870
-
.venv\Scripts\activate # On Windows
871
-
```
872
-
873
-
If your installation uses a different venv name or location, activate that one instead. All subsequent `pipelex` and `pytest` commands assume the venv is active.
874
-
875
862
### Example to execute a pipeline with text output
876
863
877
864
```python
@@ -1146,7 +1133,7 @@ Presets are meant to record the choice of an llm with its hyper parameters (temp
1146
1133
Examples:
1147
1134
```toml
1148
1135
llm_to_engineer = { model = "base-claude", temperature = 1 }
1149
-
llm_to_extract_invoice = { model = "claude-3-7-sonnet", temperature = 0.1, max_tokens = "auto" }
1136
+
llm_to_extract_invoice = { model = "claude-4.5-sonnet", temperature = 0.1, max_tokens = "auto" }
1150
1137
```
1151
1138
1152
1139
The interest is that these presets can be used to set the LLM choice in a PipeLLM, like this:
Copy file name to clipboardExpand all lines: .cursor/rules/run_pipelex.mdc
-15Lines changed: 0 additions & 15 deletions
Original file line number
Diff line number
Diff line change
@@ -6,21 +6,6 @@ globs:
6
6
---
7
7
# Guide to execute a pipeline and write example code
8
8
9
-
## Prerequisites: Virtual Environment
10
-
11
-
**CRITICAL**: Before running any `pipelex` commands or `pytest`, you MUST activate the appropriate Python virtual environment. Without proper venv activation, these commands will not work.
12
-
13
-
For standard installations, the virtual environment is named `.venv`. Always check this first:
14
-
15
-
```bash
16
-
# Activate the virtual environment (standard installation)
17
-
source .venv/bin/activate # On macOS/Linux
18
-
# or
19
-
.venv\Scripts\activate # On Windows
20
-
```
21
-
22
-
If your installation uses a different venv name or location, activate that one instead. All subsequent `pipelex` and `pytest` commands assume the venv is active.
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`. Use these directly or refine them when appropriate.
51
+
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`, `JSON`. Use these directly or refine them when appropriate.
52
52
53
53
**Refining Native Concepts:**
54
54
To create a concept that specializes a native concept without adding fields:
@@ -76,7 +76,7 @@ output = "ConceptName"
76
76
The pipes will all have at least this base definition.
77
77
- `inputs`: Dictionary of key being the variable used in the prompts, and the value being the ConceptName. It should ALSO LIST THE INPUTS OF THE INTERMEDIATE STEPS (if PipeSequence) or of the conditional pipes (if PipeCondition).
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`. Use these directly or refine them when appropriate.
47
+
Pipelex provides built-in native concepts: `Text`, `Image`, `PDF`, `TextAndImages`, `Number`, `Page`, `JSON`. Use these directly or refine them when appropriate.
46
48
47
49
**Refining Native Concepts:**
48
50
To create a concept that specializes a native concept without adding fields:
@@ -70,7 +72,7 @@ output = "ConceptName"
70
72
The pipes will all have at least this base definition.
71
73
-`inputs`: Dictionary of key being the variable used in the prompts, and the value being the ConceptName. It should ALSO LIST THE INPUTS OF THE INTERMEDIATE STEPS (if PipeSequence) or of the conditional pipes (if PipeCondition).
That means that the pipe validate_expense is missing the input `invoice` because one of the subpipe is needing it.
76
78
@@ -857,21 +859,6 @@ But don't write documentation unless asked explicitly to.
857
859
858
860
## Guide to execute a pipeline and write example code
859
861
860
-
### Prerequisites: Virtual Environment
861
-
862
-
**CRITICAL**: Before running any `pipelex` commands or `pytest`, you MUST activate the appropriate Python virtual environment. Without proper venv activation, these commands will not work.
863
-
864
-
For standard installations, the virtual environment is named `.venv`. Always check this first:
865
-
866
-
```bash
867
-
## Activate the virtual environment (standard installation)
868
-
source .venv/bin/activate # On macOS/Linux
869
-
## or
870
-
.venv\Scripts\activate # On Windows
871
-
```
872
-
873
-
If your installation uses a different venv name or location, activate that one instead. All subsequent `pipelex` and `pytest` commands assume the venv is active.
874
-
875
862
### Example to execute a pipeline with text output
876
863
877
864
```python
@@ -1146,7 +1133,7 @@ Presets are meant to record the choice of an llm with its hyper parameters (temp
1146
1133
Examples:
1147
1134
```toml
1148
1135
llm_to_engineer = { model = "base-claude", temperature = 1 }
1149
-
llm_to_extract_invoice = { model = "claude-3-7-sonnet", temperature = 0.1, max_tokens = "auto" }
1136
+
llm_to_extract_invoice = { model = "claude-4.5-sonnet", temperature = 0.1, max_tokens = "auto" }
1150
1137
```
1151
1138
1152
1139
The interest is that these presets can be used to set the LLM choice in a PipeLLM, like this:
0 commit comments