Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update notebook with latset interface change from CDK information + Bump up version to 0.0.5. #16

Merged
merged 2 commits into from
Apr 11, 2024
Merged

Update notebook with latset interface change from CDK information + Bump up version to 0.0.5. #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ec49d6
Update notebook with latset interface change from CDK information ext…
goldmermaid Apr 11, 2024
b6fd97e
Bump up version to 0.0.5.
goldmermaid Apr 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 23 additions & 49 deletions examples/prompt_to_extract_table_from_pdf_to_json.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -25,7 +25,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -55,7 +55,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -76,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 26,
"metadata": {},
"outputs": [
{
Expand All @@ -99,43 +99,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'result': [{\"Employee's social security number\": '758-58-5787',\n",
" 'Employer identification number (EIN)': '78-8778788',\n",
" \"Employer's name, address, and ZIP code\": 'DesignNext\\nKatham Dorbosto, Kashiani, Gopalganj\\nGopalganj, AK 8133',\n",
" 'Control number': '9',\n",
" \"Employee's first name and initial\": 'Jesan',\n",
" 'Last name': 'Rahaman',\n",
" \"State, Employer's state ID number\": 'AL',\n",
" 'Wages, tips, etc.': '80000.00',\n",
" 'Federal income tax withheld': '10368.00',\n",
" 'Social security tax withheld': '4960.00',\n",
" 'Medicare wages and tips': '80000.00',\n",
" 'Medicare tax withheld': '1160.00'}],\n",
" 'log': {'instruction': \"Return table in a JSON format with each box's key and value.\",\n",
" 'source': '',\n",
" 'usage': {'input_tokens': 1752, 'output_tokens': 226},\n",
" 'source_log': None},\n",
" 'page_num': 0}]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa_result"
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 27,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -184,12 +148,12 @@
" <td>Jesan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Last name</th>\n",
" <th>Employee's last name</th>\n",
" <td>Rahaman</td>\n",
" </tr>\n",
" <tr>\n",
" <th>State, Employer's state ID number</th>\n",
" <td>AL</td>\n",
" <td>AL 877878878</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Wages, tips, etc.</th>\n",
Expand All @@ -211,6 +175,14 @@
" <th>Medicare tax withheld</th>\n",
" <td>1160.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>State wages, tips, etc.</th>\n",
" <td>80000.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>State income tax</th>\n",
" <td>3835.00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
Expand All @@ -222,22 +194,24 @@
"Employer's name, address, and ZIP code DesignNext\\nKatham Dorbosto, Kashiani, Gopalga...\n",
"Control number 9\n",
"Employee's first name and initial Jesan\n",
"Last name Rahaman\n",
"State, Employer's state ID number AL\n",
"Employee's last name Rahaman\n",
"State, Employer's state ID number AL 877878878\n",
"Wages, tips, etc. 80000.00\n",
"Federal income tax withheld 10368.00\n",
"Social security tax withheld 4960.00\n",
"Medicare wages and tips 80000.00\n",
"Medicare tax withheld 1160.00"
"Medicare tax withheld 1160.00\n",
"State wages, tips, etc. 80000.00\n",
"State income tax 3835.00"
]
},
"execution_count": 8,
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = qa_result[0]['result']\n",
"data = qa_result[0]\n",
"keys = [list(item.keys()) for item in data][0]\n",
"values = [list(item.values()) for item in data][0]\n",
"\n",
Expand Down Expand Up @@ -277,7 +251,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
"version": "3.10.14"
}
},
"nbformat": 4,
Expand Down
136 changes: 65 additions & 71 deletions examples/prompt_to_extract_table_from_pdf_to_json_advanced_mode.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -25,7 +25,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -55,7 +55,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -76,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 24,
"metadata": {},
"outputs": [
{
Expand All @@ -99,52 +99,51 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{\"a Employee's social security number\": '758-58-5787',\n",
" 'b Employer identification number (EIN)': '78-8778788',\n",
" \"c Employer's name, address, and ZIP code\": 'DesignNext\\nKatham Dorbosto, Kashiani, Gopalganj\\nGopalganj, AK 8133',\n",
" 'd Control number': '9',\n",
" \"e Employee's first name and initial\": 'Jesan',\n",
" \"e Employee's last name\": 'Rahaman',\n",
" \"f Employee's address and ZIP code\": 'AL 877878878',\n",
" '1 Wages, tips, other compensation': '80000.00',\n",
" '2 Federal income tax withheld': '10368.00',\n",
" '3 Social security wages': '80000.00',\n",
" '4 Social security tax withheld': '4960.00',\n",
" '5 Medicare wages and tips': '80000.00',\n",
" '6 Medicare tax withheld': '1160.00',\n",
" '7 Social security tips': 'NA',\n",
" '8 Allocated tips': 'NA',\n",
" '10 Dependent care benefits': 'NA',\n",
" '11 Nonqualified plans': 'NA',\n",
" '13 Statutory Retroment employee plan': 'NA',\n",
" '13 Third-party sick pay': 'NA',\n",
" '14 Other': 'NA',\n",
" \"15 State Employer's state ID number\": 'AL',\n",
" '16 State wages, tips, etc.': '80000.00',\n",
" '17 State income tax': '3835.00',\n",
" '18 Local wages, tips, etc.': 'NA',\n",
" '19 Local income tax': 'NA',\n",
" '20 Locality name': 'NA'}]"
"[[{\"a Employee's social security number\": '758-58-5787',\n",
" 'b Employer identification number (EIN)': '78-8778788',\n",
" \"c Employer's name, address, and ZIP code\": 'DesignNext\\nKatham Dorbosto, Kashiani, Gopalganj\\nGopalganj, AK 8133',\n",
" 'd Control number': '9',\n",
" \"e Employee's first name and initial\": 'Jesan',\n",
" 'e Last name': 'Rahaman',\n",
" \"f Employee's address and ZIP code\": 'AL\\n877878878',\n",
" '1 Wages, tips, other compensation': '80000.00',\n",
" '2 Federal income tax withheld': '10368.00',\n",
" '3 Social security wages': '80000.00',\n",
" '4 Social security tax withheld': '4960.00',\n",
" '5 Medicare wages and tips': '80000.00',\n",
" '6 Medicare tax withheld': '1160.00',\n",
" '7 Social security tips': 'NA',\n",
" '8 Allocated tips': 'NA',\n",
" '10 Dependent care benefits': 'NA',\n",
" '11 Nonqualified plans': 'NA',\n",
" '13 Statutory Retroment employee Third-party sick pay plan': 'NA',\n",
" '14 Other': 'NA',\n",
" '15 State': 'AL',\n",
" '16 State wages, tips, etc.': '80000.00',\n",
" '17 State income tax': '3835.00',\n",
" '18 Local wages, tips, etc.': 'NA',\n",
" '19 Local income tax': 'NA',\n",
" '20 Locality name': 'NA'}]]"
]
},
"execution_count": 11,
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa_result[0]['result']"
"qa_result"
]
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 27,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -193,12 +192,12 @@
" <td>Jesan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>e Employee's last name</th>\n",
" <th>e Last name</th>\n",
" <td>Rahaman</td>\n",
" </tr>\n",
" <tr>\n",
" <th>f Employee's address and ZIP code</th>\n",
" <td>AL 877878878</td>\n",
" <td>AL\\n877878878</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1 Wages, tips, other compensation</th>\n",
Expand Down Expand Up @@ -241,19 +240,15 @@
" <td>NA</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13 Statutory Retroment employee plan</th>\n",
" <td>NA</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13 Third-party sick pay</th>\n",
" <th>13 Statutory Retroment employee Third-party sick pay plan</th>\n",
" <td>NA</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14 Other</th>\n",
" <td>NA</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15 State Employer's state ID number</th>\n",
" <th>15 State</th>\n",
" <td>AL</td>\n",
" </tr>\n",
" <tr>\n",
Expand Down Expand Up @@ -281,42 +276,41 @@
"</div>"
],
"text/plain": [
" Value\n",
"a Employee's social security number 758-58-5787\n",
"b Employer identification number (EIN) 78-8778788\n",
"c Employer's name, address, and ZIP code DesignNext\\nKatham Dorbosto, Kashiani, Gopalga...\n",
"d Control number 9\n",
"e Employee's first name and initial Jesan\n",
"e Employee's last name Rahaman\n",
"f Employee's address and ZIP code AL 877878878\n",
"1 Wages, tips, other compensation 80000.00\n",
"2 Federal income tax withheld 10368.00\n",
"3 Social security wages 80000.00\n",
"4 Social security tax withheld 4960.00\n",
"5 Medicare wages and tips 80000.00\n",
"6 Medicare tax withheld 1160.00\n",
"7 Social security tips NA\n",
"8 Allocated tips NA\n",
"10 Dependent care benefits NA\n",
"11 Nonqualified plans NA\n",
"13 Statutory Retroment employee plan NA\n",
"13 Third-party sick pay NA\n",
"14 Other NA\n",
"15 State Employer's state ID number AL\n",
"16 State wages, tips, etc. 80000.00\n",
"17 State income tax 3835.00\n",
"18 Local wages, tips, etc. NA\n",
"19 Local income tax NA\n",
"20 Locality name NA"
" Value\n",
"a Employee's social security number 758-58-5787\n",
"b Employer identification number (EIN) 78-8778788\n",
"c Employer's name, address, and ZIP code DesignNext\\nKatham Dorbosto, Kashiani, Gopalga...\n",
"d Control number 9\n",
"e Employee's first name and initial Jesan\n",
"e Last name Rahaman\n",
"f Employee's address and ZIP code AL\\n877878878\n",
"1 Wages, tips, other compensation 80000.00\n",
"2 Federal income tax withheld 10368.00\n",
"3 Social security wages 80000.00\n",
"4 Social security tax withheld 4960.00\n",
"5 Medicare wages and tips 80000.00\n",
"6 Medicare tax withheld 1160.00\n",
"7 Social security tips NA\n",
"8 Allocated tips NA\n",
"10 Dependent care benefits NA\n",
"11 Nonqualified plans NA\n",
"13 Statutory Retroment employee Third-party sic... NA\n",
"14 Other NA\n",
"15 State AL\n",
"16 State wages, tips, etc. 80000.00\n",
"17 State income tax 3835.00\n",
"18 Local wages, tips, etc. NA\n",
"19 Local income tax NA\n",
"20 Locality name NA"
]
},
"execution_count": 10,
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = qa_result[0]['result']\n",
"data = qa_result[0]\n",
"keys = [list(item.keys()) for item in data][0]\n",
"values = [list(item.values()) for item in data][0]\n",
"\n",
Expand Down
Loading
Loading