Skip to content

Commit 9a768c3

Browse files
marcvergeesLochit-Vinay
authored andcommitted
docs: 📝 wiki pages start
1 parent 74b14d1 commit 9a768c3

10 files changed

Lines changed: 203 additions & 362 deletions

File tree

docs/DEPLOYMENT.md

Lines changed: 0 additions & 240 deletions
This file was deleted.

docs/db.md

Lines changed: 0 additions & 48 deletions
This file was deleted.

docs/docker.md

Lines changed: 0 additions & 70 deletions
This file was deleted.
Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# FireForm Architecture
22

3-
FireForm is a system designed to automate the process of filling out PDF forms using information extracted from transcriptions (e.g., voice recordings) via an LLM.
3+
FireForm is a system designed to automate the process of filling out PDF forms using information extracted from transcriptions via an LLM.
44

55
## Pipeline Description
66

@@ -11,7 +11,7 @@ The FireForm pipeline follows a structured flow from receiving raw user input to
1111
1. **Template Preparation**: A standard PDF is processed to ensure it has interactive form fields.
1212
2. **Input Acquisition**: The system receives a transcript (text) and a list of target fields to extract.
1313
3. **LLM Extraction**: An LLM (via Ollama) processes the transcript to find values for each target field.
14-
4. **Form Filling**: extracted values are mapped and written into the PDF template.
14+
4. **Form Filling**: Extracted values are mapped and written into the PDF template.
1515
5. **Output Generation**: A new, filled PDF is saved with a timestamped filename.
1616

1717
### Component Interaction
@@ -55,7 +55,7 @@ sequenceDiagram
5555
### Key Components
5656

5757
- **`FileManipulator`**: The high-level orchestrator that manages the overall process.
58-
- **`LLM`**: Handles prompt engineering and communication with the local Ollama instance (typically using the Mistral model). It extracts structured data from unstructured text.
59-
- **`Filler`**: Handles the low-level PDF manipulation, ensuring that extracted data is placed into the correct form fields based on their visual order.
58+
- **`LLM`**: Handles prompt engineering and communication with the local Ollama instance. It extracts structured data from unstructured text.
59+
- **`Filler`**: Handles the low-level PDF manipulation, ensuring that extracted data is placed into the correct form fields.
6060
- **`commonforms`**: A dependency used to prepare standard PDFs for filling.
6161
- **`pdfrw` / `pypdf`**: Libraries used for reading and writing PDF metadata and form field values.

0 commit comments

Comments
 (0)