run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-07-18 07:44:41 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

ValueError: Could not extract json string from output (with correct output) #181

New Issue
Open
opened 2026-02-16 00:17:04 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:04 -05:00
Owner
Copy Link
Copy Source

Originally created by @jakubstrawa1 on GitHub (Jul 11, 2024).

When using LLMTextCompletionProgram to incorporate the pydantic modelling for my output i get a very strange result. The error indicates that the output is proper (134436839ABCDFG), but it still throws an error that it cannot extract json string from output. Any ideas why this is happening?

LLM im using is gpt 3.5 turbo

pip list

llama-cloud                             0.0.6
llama-index                             0.10.54
llama-index-agent-openai                0.1.7
llama-index-cli                         0.1.12
llama-index-core                        0.10.53.post1
llama-index-embeddings-openai           0.1.10
llama-index-indices-managed-llama-cloud 0.2.4
llama-index-legacy                      0.9.48
llama-index-llms-openai                 0.1.25
llama-index-multi-modal-llms-openai     0.1.7
llama-index-postprocessor-cohere-rerank 0.1.7
llama-index-program-openai              0.1.6
llama-index-question-gen-openai         0.1.3
llama-index-readers-file                0.1.30
llama-index-readers-llama-parse         0.1.6
llama-parse                             0.4.6

question= "Extract the 'LEI' for the company from the text. The 'ABC' should be in the format XXXXXXXXXXXXXXXXXXXX, where X can be either a number or an uppercase letter (e.g., 529900QF6F5IB9WQCL03). Please respond with only the LEI and no additional information. Return 'No info' if no ABCis found."

prompt= json_val['prompts']['prompt_template'].format(question=question, context=processed_document)
llm_completion = LLMTextCompletionProgram.from_defaults(
    llm=llm,
    output_cls=ABC,
    prompt_template_str=prompt,
    verbose=True,
)

x = llm_completion()

ValueError: Could not extract json string from output: "ABC": "134436839ABCDFG"

Pydantic model looks like this

class ABC(BaseModel):

    abc: str = Field(..., description="The 'ABC' or 'No info' if it doesn't exist.")

    @validator("abc")
    def validate_lei_code(cls, v):
        if v.lower() != "no info" and not re.match(r"^[0-9]{4}[0]{2}[A-Z0-9]{12}[0-9]{2}$", v):
            raise ValueError("Invalid ABC code format")
        return v
Originally created by @jakubstrawa1 on GitHub (Jul 11, 2024). When using LLMTextCompletionProgram to incorporate the pydantic modelling for my output i get a very strange result. The error indicates that the output is proper (134436839ABCDFG), but it still throws an error that it cannot extract json string from output. Any ideas why this is happening? LLM im using is gpt 3.5 turbo pip list ``` llama-cloud 0.0.6 llama-index 0.10.54 llama-index-agent-openai 0.1.7 llama-index-cli 0.1.12 llama-index-core 0.10.53.post1 llama-index-embeddings-openai 0.1.10 llama-index-indices-managed-llama-cloud 0.2.4 llama-index-legacy 0.9.48 llama-index-llms-openai 0.1.25 llama-index-multi-modal-llms-openai 0.1.7 llama-index-postprocessor-cohere-rerank 0.1.7 llama-index-program-openai 0.1.6 llama-index-question-gen-openai 0.1.3 llama-index-readers-file 0.1.30 llama-index-readers-llama-parse 0.1.6 llama-parse 0.4.6 ``` ``` question= "Extract the 'LEI' for the company from the text. The 'ABC' should be in the format XXXXXXXXXXXXXXXXXXXX, where X can be either a number or an uppercase letter (e.g., 529900QF6F5IB9WQCL03). Please respond with only the LEI and no additional information. Return 'No info' if no ABCis found." prompt= json_val['prompts']['prompt_template'].format(question=question, context=processed_document) llm_completion = LLMTextCompletionProgram.from_defaults( llm=llm, output_cls=ABC, prompt_template_str=prompt, verbose=True, ) x = llm_completion() ``` ValueError: Could not extract json string from output: "ABC": "134436839ABCDFG" Pydantic model looks like this ``` class ABC(BaseModel): abc: str = Field(..., description="The 'ABC' or 'No info' if it doesn't exist.") @validator("abc") def validate_lei_code(cls, v): if v.lower() != "no info" and not re.match(r"^[0-9]{4}[0]{2}[A-Z0-9]{12}[0-9]{2}$", v): raise ValueError("Invalid ABC code format") return v ```
yindo added the bug label 2026-02-16 00:17:04 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#181
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?