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
Copy file name to clipboardExpand all lines: en/ai/local-llm.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -38,7 +38,7 @@ Now, you are all set and can chat "locally".
38
38
The following steps guide you on how to use `GPT4All`to download and run local LLMs.
39
39
40
40
1. Install `GPT4All`from their [website](https://www.nomic.ai/gpt4all).
41
-
2. Open GPT4All, [download a model](https://docs.gpt4all.io/gpt4all_desktop/models.html), configure it in the[settings](https://docs.gpt4all.io/gpt4all_desktop/settings.html) and [run it as a server](https://docs.gpt4all.io/gpt4all_api_server/home.html).
41
+
2. Open GPT4All, [download a model](https://docs.gpt4all.io/gpt4all_desktop/models.html), configure it in the[settings](https://docs.gpt4all.io/gpt4all_desktop/settings.html) and [run it as a server](https://docs.gpt4all.io/gpt4all_api_server/home.html).
42
42
3. Open JabRef, go to "File" > "Preferences" > "AI"
43
43
4. Set the "AI provider" to "GPT4All"
44
44
5. Set the "Chat model" to the name (including the `.gguf`part) of the model you have downloaded in GPT4All.
4. Choose a start directory using the "Browse" button.
49
49
5. Click on "Search" / "Scan directory".
50
-
6.In "Select files", the files not yet contained in the library are shown.
50
+
6. In "Select files", the files not yet contained in the library are shown.
51
51
52
52
<imgsrc="../.gitbook/assets/findunlinkedfiles-foundfiles-5.2 (6).png"alt="FindUnlinkedFiles - Found files"data-size="original">
53
53
7. Select the entries you are interested in. Note: the button `Export selected files` allows you to export the list of the selected files (a text file containing on each line one filename with its path)
54
-
8.Click on `Import`.
54
+
8. Click on `Import`.
55
55
56
56
The windows close and the entry table now contains the newly-imported entries.
57
57
9. The entry editor with the last imported entry is shown .png>)
<divalign="left"><figure><picture><sourcesrcset="../.gitbook/assets/Bild 3 - paste text - dark mode (2).png"media="(prefers-color-scheme: dark)"><imgsrc="../.gitbook/assets/new-entry-from-plain-text-step-3 (1).png"alt=""></picture><figcaption></figcaption></figure></div>
34
-
4. Choose a parser from the drop-down menu.
30
+
31
+
4. Choose a parser from the drop-down menu.
35
32
36
33
<divalign="left"><figure><picture><sourcesrcset="../.gitbook/assets/Bild 4 - Parser Choise (Rule-based, Grobid and LLM) - dark mode.png"media="(prefers-color-scheme: dark)"><imgsrc="../.gitbook/assets/Bild 4 - Parser Choise (Rule-based, Grobid and LLM) - light mode.png"alt=""></picture><figcaption></figcaption></figure></div>
37
-
5. Click "Add to current library"
38
-
6. The result is selected in the entry table:
39
34
35
+
5. Click "Add to current library"
40
36
37
+
6. The result is selected in the entry table:
41
38
42
39
<figure><picture><sourcesrcset="../.gitbook/assets/Bild 5 - rule based result is selected in entry table - dark mode.png"media="(prefers-color-scheme: dark)"><imgsrc="../.gitbook/assets/Bild 5 - rule based result is selected in entry table - light mode.png"alt=""></picture><figcaption></figcaption></figure>
43
40
44
-
###Parser Explanation
41
+
## Parser Explanation
45
42
46
-
####Rule-based
43
+
### Rule-based
47
44
48
45
This is the default parser. It does not require any extensive setups, nor does it send data to remote services. Any conversions are executed locally on your device. The rule-based parser also is deterministic, as the rules are hard-coded. Unfortunately, at time of writing, the rule-based parser is far from perfect. As one can see in the example above, the number "10" was wrongly interpreted as a page number, which is clearly not the intended result. The underlying rules are insufficient to account for all possibilities that bibliographic metadata may contain and ideally would require a way more fine-grained, but an ever more complex rule-set. It is recommended to use the rule-based parser as a last-resort, when the Grobid or LLM based parsers are not available or not desireable.
49
46
50
-
####Grobid
47
+
### Grobid
51
48
52
49
JabRef uses the technology offered by [Grobid](https://github.com/kermitt2/grobid), a machine learning software project with decades of experience and development dedicated to bibliographic metadata extraction. The Grobid parser usually tends to achieve better results than the rule-based parser. Since JabRef runs Grobid on a remote instance, users will have to confirm sending data to JabRef's online service in the preferences (_File > Preferences > Web search > Remote Services_). Sending data is disabled by default. It cannot be guaranteed that JabRef's Grobid instance will always be up and running, but it is possible for you to set up your [own Grobid Instance](https://grobid.readthedocs.io/en/latest/Grobid-docker/).
53
50
54
51
<figure><picture><sourcesrcset="../.gitbook/assets/Bild 6 - Grobid Preferences - dark mode.png"media="(prefers-color-scheme: dark)"><imgsrc="../.gitbook/assets/Bild 6 - Grobid Preferences - light mode.png"alt=""></picture><figcaption><p>Grobid related preference section in JabRef</p></figcaption></figure>
55
52
56
-
####LLM
53
+
### LLM
57
54
58
55
Large Language Models too can be used to convert the reference text. The quality of the results is surprisingly good, tends to be better than the rule-based parser and competes with Grobid. Nevertheless, it depends on the model or service that is used and if they are trained/designed for this use-case. Extensive documentation about how to set up a local LLM or connect to a remote AI service can be found in the [AI functionality](../ai/) section. Data privacy depends on the external application that you are using to run the local model and/or on the remote AI provider, if you are connecting to one of those.
Copy file name to clipboardExpand all lines: en/contributing/how-to-translate-the-ui.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,3 +1,5 @@
1
+
<!-- markdownlint-disable MD033 -->
2
+
1
3
# How to translate the JabRef User Interface
2
4
3
5
## Introduction
@@ -11,10 +13,10 @@ If the JabRef interface already exists in your language, you can help improve it
11
13
We use the service of [Crowdin](https://translate.jabref.org) to keep our translations updated. It is a service directly running in the browser and one can quickly join and start translating.
12
14
13
15
* Visit [https://translate.jabref.org/](https://translate.jabref.org) to get started
14
-
*Select your preferred language, login, and click on _JabRef\_en.properties_
16
+
* Select your preferred language, login, and click on _JabRef\_en.properties_
15
17
16
18
<imgsrc="../.gitbook/assets/crowdin-select-file (4).png"alt="Screenshot of Crowdin select file page"data-size="original">
17
-
*Choose the string you want to translate in the left panel (strings to be translated are listed first)
19
+
* Choose the string you want to translate in the left panel (strings to be translated are listed first)
18
20
19
21
and enter the translation in the central panel (suggestions are given at the bottom)
Copy file name to clipboardExpand all lines: en/finding-sorting-and-cleaning-entries/filelinks.md
+5-2Lines changed: 5 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,3 +1,5 @@
1
+
<!-- markdownlint-disable MD033 -->
2
+
1
3
# Manage associated files
2
4
3
5
JabRef lets you link up your entries with files of any type stored on your system. Thereby, it uses the field `file`, which contains a list of linked files. Each entry can have an arbitrary number of file links, and each linked file can be opened quickly from JabRef. The fields `url` and `doi` are used as links to documents on the web in the form of a URL or a DOI identifier, respectively (see [URL and DOI in JabRef](../advanced/externalfiles.md)).
@@ -14,9 +16,10 @@ If the "file" field is included in [General fields](../setup/generalfields.md),
Copy file name to clipboardExpand all lines: en/setup/citationkeypatterns.md
+6-4Lines changed: 6 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,3 +1,5 @@
1
+
<!-- markdownlint-disable MD033 -->
2
+
1
3
# Customize the citation key generator
2
4
3
5
The pattern used in the auto generation of citation labels can be set for each of the standard entry types in **File → Preferences**, tab **Citation key generator**. A detailed description can be found in the [default citation key pattern section](citationkeypatterns.md#default-citation-key-pattern).
@@ -184,9 +186,9 @@ To change the citation key patterns for a single library to `[auth][shortyear]`,
184
186
1. Make sure the library is open and selected in the JabRef main window
0 commit comments