[Feat] Accept non-dict if only 1 prompt input variable #19156
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
nfcampos
approved these changes
Mar 16, 2024
dosubot
bot
added
the
lgtm
dosubot
bot
added
the
size:S
hinthornw
changed the title
eyurtsev
reviewed
Mar 19, 2024
|
|
||
| def test_messages_prompt_accepts_list() -> None: | ||
| prompt = ChatPromptTemplate.from_messages([MessagesPlaceholder("history")]) | ||
| value = prompt.invoke([("user", "Hi there")]) # type: ignore |
There was a problem hiding this comment.
his is confusing -- are we sure we want to support?, why is it a list of 2-tuples rather than only a 2-tuple?
There was a problem hiding this comment.
We already support prompt.invoke({"history": [("user", "hi there"]})
eyurtsev
approved these changes
Mar 20, 2024
dosubot
bot
added
size:M
hinthornw
force-pushed
the
wfh/accept_messages_list
branch
from
c357868
to
1b9de31
Compare
hinthornw
commented
Mar 20, 2024
| and you invoke the template with a non-dict object, the prompt template will | ||
| inject the provided argument into that variable location. | ||
|
|
||
| Single-variable template: |
There was a problem hiding this comment.
@baskaryan do you think this formatting would work?
There was a problem hiding this comment.
this should be indented at same level as Examples: (L564)
rahul-trip
pushed a commit
to daxa-ai/langchain
that referenced
this pull request
Mar 27, 2024
…19156) For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
bechbd
pushed a commit
to bechbd/langchain
that referenced
this pull request
Mar 29, 2024
…19156) For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
gkorland
pushed a commit
to FalkorDB/langchain
that referenced
this pull request
Mar 30, 2024
…19156) For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
chrispy-snps
pushed a commit
to chrispy-snps/langchain
that referenced
this pull request
Mar 30, 2024
…19156) For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
chrispy-snps
pushed a commit
to chrispy-snps/langchain
that referenced
this pull request
Mar 30, 2024
…19156) For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
hinthornw
added a commit
that referenced
this pull request
Apr 26, 2024
For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting.
The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before